PageSourceSearch

https://ashutosh887.vercel.app/writing/evals-are-the-product

html ashutosh887.vercel.app collected 2026-10-03 06:07:37 UTC 151,485 bytes, 6 lines download raw bytes

1<!DOCTYPE html><html lang="en-IN" class="bricolage_grotesque_6c0e643-module___gO8iW__variable geist_d633ac5f-module__BboVrW__variable geist_mono_768fb615-module__nw7kYW__variable"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" href="/_next/static/immutable/media/017d9bea37084d9b-s.p.2fl0vhx7oyatw.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="preload" href="/_next/static/immutable/media/797e433ab948586e-s.p.1v5bejj26fx9h.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="preload" href="/_next/static/immutable/media/caa3a2e1cccd8315-s.p.0zr6hhvz-h9nw.woff2" as="font" crossorigin="" type="font/woff2"/><link rel="stylesheet" href="/_next/static/immutable/chunks/2l4hswa-ubkpn.css" data-precedence="next"/><link rel="preload" as="script" fetchPriority="low" href="/_next/static/immutable/chunks/2belr3pe9fbiz.js"/>
1<script src="/_next/static/immutable/chunks/0ws7t_wz4dvp7.js" async=""></script>
1<script src="/_next/static/immutable/chunks/338f3b2xexm1o.js" async=""></script>
1<script src="/_next/static/immutable/chunks/2-fg1b3gspk0j.js" async=""></script>
1<script src="/_next/static/immutable/chunks/turbopack-23m1e49ipg998.js" async=""></script>
1<script src="/_next/static/immutable/chunks/19s7px060v539.js" async="" crossorigin=""></script>
1<script src="/_next/static/immutable/chunks/1a_43ptwezuwl.js" async="" crossorigin=""></script>
1<script src="/_next/static/immutable/chunks/09dv42b2n4kp8.js" async="" crossorigin=""></script>
1<script src="/_next/static/immutable/chunks/2ffteh9vf_1wl.js" async="" crossorigin=""></script>
1<script src="/_next/static/immutable/chunks/0q4r2h8-bzpex.js" async="" crossorigin=""></script>
1<script src="/_next/static/immutable/chunks/0gr14mxkka9yj.js" async="" crossorigin=""></script>
1<script src="/_next/static/immutable/chunks/1tf2pn9278k7y.js" async="" crossorigin=""></script>
1<script src="/_next/static/immutable/chunks/0xbp3crmj8tk4.js" async="" crossorigin=""></script>
1<script src="/_next/static/immutable/chunks/2pa3wur8avg6r.js" async="" crossorigin=""></script>
1<meta name="theme-color" content="#0a0a0a"/><title>Evals are the product - Ashutosh Jha</title><meta name="description" content="Ship an LLM feature and the eval suite becomes the spec, whether you meant it to or not. Write it like one from the start."/><meta name="application-name" content="Ashutosh Jha Portfolio"/><link rel="author" href="https://www.ashutosh887.in"/><meta name="author" content="Ashutosh Jha"/><link rel="manifest" href="/manifest.webmanifest"/><meta name="keywords" content="Hire Ashutosh Jha,Ashutosh Jha for hire,Hire Software Engineer Bengaluru,Hire Full Stack Developer India,Hire AI Engineer,Hire Cloud Engineer,Hire Web3 Developer,Ashutosh Jha,Ashutosh Jha Software Engineer,Ashutosh Jha Full Stack Developer,Ashutosh Jha AI Developer,Ashutosh Jha Web3 Developer,Ashutosh Jha Portfolio,Ashutosh Jha GitHub,Ashutosh Jha LinkedIn,ashutosh887,Software Engineer,Full Stack Developer,Full Stack Engineer,AI Engineer,AI and Full Stack Engineer,Infrastructure Engineer,Cloud Engineer,Machine Learning Engineer,Web3 Developer,Blockchain Developer,Developer Relations Engineer,Frontend Developer,Backend Developer,React Developer,Next.js Developer,Node.js Developer,TypeScript Developer,Python Developer,Go Developer,OpenAI Developer,GPT-4 Developer,Solana Developer,React.js,Next.js,Node.js,TypeScript,JavaScript,Python,Go,PostgreSQL,MongoDB,Redis,Docker,Kubernetes,AWS,Amazon EC2,Amazon S3,Amazon Aurora,Aurora DSQL,Google Cloud,Google Cloud Run,ClickHouse,Observability,OpenAI API,GPT-4 API,Google Gemini,Solana,Anchor Framework,Smart Contracts,Web3,Blockchain,REST API,WebSockets,Microservices,Insitu Engineer,AI Infrastructure Engineer,LLM Engineer,Agent Systems Engineer,RAG Engineer,South Park Commons Engineer,Transak Developer,CubeAPM Engineer,Stub,NeverLose,FinQuery,Evolv,WinterArc,StudioCast,saathi,ClickLiv,Plumb,Darwin,ClawGuard,Stoq,verdex,BridgeRadar,moodcast,FeelTheWeb,depextract,ethsapien,PayFlow,Portkey AI Builder Challenge Winner,Pine Labs AI Hackathon Finalist,Ethereum Payment Workflows,Prompt Engineering Platform,AlivePing,SafeVoice,ShotLock,CareerFit,LaunchKit,CivicLens,Voice AI,CIBA,x402,Cross-chain,Bridging risk,Bengaluru Software Engineer,Bengaluru Developer,Karnataka Developer,India Software Engineer,India Developer,Remote Software Engineer,AI-powered applications,AI chatbot developer,Slack bot developer,WhatsApp bot developer,SDK developer,Developer tools,Browser extension developer,Real-time applications,Scalable applications,Performance optimization,System design,API development"/><meta name="referrer" content="origin-when-cross-origin"/><meta name="creator" content="Ashutosh Jha"/><meta name="publisher" content="Ashutosh Jha"/><meta name="robots" content="index, follow"/><meta name="googlebot" content="index, follow, max-video-preview:-1, max-image-preview:large, max-snippet:-1"/><meta name="category" content="Technology"/><meta name="classification" content="Portfolio Website"/><meta name="apple-mobile-web-app-capable" content="yes"/><meta name="apple-mobile-web-app-status-bar-style" content="black-translucent"/><meta name="apple-mobile-web-app-title" content="Ashutosh Jha"/><meta name="mobile-web-app-capable" content="yes"/><meta name="msapplication-TileColor" content="#0a0a0a"/><meta name="profile:first_name" content="Ashutosh"/><meta name="profile:last_name" content="Jha"/><meta name="profile:username" content="ashutosh887"/><meta name="og:profile:first_name" content="Ashutosh"/><meta name="og:profile:last_name" content="Jha"/><link rel="canonical" href="https://www.ashutosh887.in/writing/evals-are-the-product"/><link rel="alternate" type="application/rss+xml" href="https://www.ashutosh887.in/feed.xml"/><meta property="og:title" content="Evals are the product - Ashutosh Jha"/><meta property="og:description" content="Ship an LLM feature and the eval suite becomes the spec, whether you meant it to or not. Write it like one from the start."/><meta property="og:url" content="https://www.ashutosh887.in/writing/evals-are-the-product"/><meta property="og:image" content="https://www.ashutosh887.in/writing/evals-are-the-product/opengraph-image?0c852efdf562a8d4"/><meta property="og:image:type" content="image/png"/>
1<meta property="og:image:width" content="1200"/><meta property="og:image:height" content="630"/><meta property="og:type" content="article"/><meta property="article:published_time" content="2026-06-12"/><meta property="article:modified_time" content="2026-06-12"/><meta property="article:author" content="https://www.ashutosh887.in"/><meta property="article:tag" content="ai"/><meta property="article:tag" content="llm"/><meta property="article:tag" content="evals"/><meta property="article:tag" content="machine-learning"/><meta name="twitter:card" content="summary_large_image"/><meta name="twitter:title" content="Evals are the product - Ashutosh Jha"/><meta name="twitter:description" content="Ship an LLM feature and the eval suite becomes the spec, whether you meant it to or not. Write it like one from the start."/><meta name="twitter:image" content="https://www.ashutosh887.in/writing/evals-are-the-product/opengraph-image?0c852efdf562a8d4"/><meta name="twitter:image:type" content="image/png"/><meta name="twitter:image:width" content="1200"/><meta name="twitter:image:height" content="630"/><link rel="icon" href="/icon?29b4dc8a27dd18bc" type="image/png" sizes="512x512"/><link rel="apple-touch-icon" href="/apple-icon?f0d5e0f0fa426977" type="image/png" sizes="180x180"/><meta name="next-size-adjust" content=""/><link rel="preconnect" href="https://www.googletagmanager.com" crossorigin="anonymous"/><link rel="preconnect" href="https://www.clarity.ms" crossorigin="anonymous"/><link rel="dns-prefetch" href="https://www.googletagmanager.com"/><link rel="dns-prefetch" href="https://www.clarity.ms"/><meta name="geo.region" content="IN-KA"/><meta name="geo.placename" content="Bengaluru"/><meta name="geo.position" content="12.9716;77.5946"/><meta name="ICBM" content="12.9716, 77.5946"/>
1<script>(function(){try{var t=localStorage.getItem("portfolio-theme");if(!t||["cyan","violet","emerald","amber","rose"].indexOf(t)<0){t="cyan"}document.documentElement.dataset.theme=t}catch(e){document.documentElement.dataset.theme="cyan"}})()</script>
1<script type="application/ld+json">{"@context":"https://schema.org","@graph":[{"@context":"https://schema.org","@type":"Person","@id":"https://www.ashutosh887.in/#person","name":"Ashutosh Jha","givenName":"Ashutosh","familyName":"Jha","jobTitle":"AI and Full Stack Engineer","description":"AI and Full Stack Engineer at Insitu in Bengaluru. Builds agent budgets, voice workflows, vision adjudication, and streaming telemetry on ClickHouse and Aurora DSQL.","worksFor":{"@type":"Organization","name":"Insitu"},"url":"https://www.ashutosh887.in","mainEntityOfPage":"https://www.ashutosh887.in","sameAs":["https://github.com/ashutosh887","https://stackoverflow.com/users/14923299/ashutosh887","https://leetcode.com/u/ashutosh887/","https://codeforces.com/profile/ashutosh887","https://www.linkedin.com/in/ashutosh887","https://x.com/ashutosh887_","https://instagram.com/ashutosh887_","https://www.credly.com/users/ashutosh887"],"memberOf":[{"@type":"OrganizationRole","roleName":"Organising Team","startDate":"2025","memberOf":{"@type":"Organization","name":"AWS User Group Bengaluru","url":"https://www.meetup.com/awsugblr/"}},{"@type":"OrganizationRole","roleName":"Volunteer Team","startDate":"2023","memberOf":{"@type":"Organization","name":"DevOpsDays Bengaluru","url":"https://devopsdays.org/events/2023-bengaluru/welcome/"}},{"@type":"OrganizationRole","roleName":"Chapter Lead, Bhopal and Karnataka","startDate":"2022","endDate":"2024","memberOf":{"@type":"Organization","name":"The Phoenix Guild","url":"https://x.com/PhoenixGuildHQ/status/1663918942853668866"}}],"email":"[email protected]","address":{"@type":"PostalAddress","addressLocality":"Bengaluru","addressRegion":"Karnataka","addressCountry":"IN"},"alumniOf":{"@type":"EducationalOrganization","name":"Lakshmi Narain College of Technology","address":{"@type":"PostalAddress","addressLocality":"Bhopal","addressRegion":"Madhya Pradesh","addressCountry":"IN"}},"knowsAbout":["Software Engineering","Artificial Intelligence","LLM and Agent Systems","AI Infrastructure","Retrieval-Augmented Generation","Vector Search","Semantic Embeddings","Prompt Engineering","Model Context Protocol","Reinforcement Learning","Machine Learning","Full Stack Development","Distributed Backends","Data Pipelines","Observability","Cloud Infrastructure","Amazon Web Services","Amazon EC2","Amazon S3","Amazon Aurora","Aurora DSQL","Google Cloud","Google Cloud Run","Docker","Kubernetes","Redis","ClickHouse","PostgreSQL","React.js","Next.js","Node.js","FastAPI","TypeScript","Python","Go","Solidity","OpenAI API","GPT-4","Anthropic Claude","Voice AI","CIBA","Web3 Development","Smart Contracts","Payment Workflows","x402","Cross-chain","Bridging risk","Solana","Ethereum","Hardhat"],"hasOccupation":{"@type":"Occupation","name":"AI and Full Stack Engineer","occupationLocation":{"@type":"City","name":"Bengaluru"},"skills":"JavaScript, TypeScript, Python, Go, Java, SQL, Solidity, Rust, React.js, Next.js, React Native, Redux, TailwindCSS, HTML5, CSS3, Node.js, Express.js, NestJS, FastAPI, REST APIs, WebSockets, Microservices, OpenAI API, GPT-4, Anthropic Claude, Google Gemini API, LLMs, AI Agents, RAG, Vector Search, Semantic Embeddings, Evals, Prompt Engineering, LangChain, Model Context Protocol, Reinforcement Learning, Voice AI, CIBA, PostgreSQL, MongoDB, Redis, ClickHouse, Supabase, Firebase, Prisma ORM, Solana, Anchor Framework, Polkadot.js, Smart Contracts, Web3, DApps, Ethereum, x402, Cross-chain, Bridging risk, AWS, Amazon EC2, Amazon S3, Amazon Aurora, Aurora DSQL, Google Cloud, Google Cloud Run, Docker, Kubernetes, CI/CD, GitHub Actions, Linux, Observability, Datadog, Confluent, Git, Postman, Figma, Jest, System Design, Performance Optimization"},"hasCredential":[{"@type":"EducationalOccupationalCredential","credentialCategory":"degree","educationalLevel":"Bachelor's Degree","name":"Bachelor of Technology in Computer Science Engineering","about":{"@type":"EducationalOrganization","name":"Lakshmi Narain College of Technology"}},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/16fd70e2-0188-4dde-b896-bdcbbb9aaeb9#credential","credentialCategory":"certification","name":"Claude Certified Developer - Foundations","url":"https://www.credly.com/badges/16fd70e2-0188-4dde-b896-bdcbbb9aaeb9","identifier":"16fd70e2-0188-4dde-b896-bdcbbb9aaeb9","dateCreated":"2026-09-27","expires":"2027-09-27","image":"https://www.ashutosh887.in/images/badges/claude-certified-developer-foundations.png","recognizedBy":{"@type":"Organization","name":"Anthropic"},"competencyRequired":["Agent development","Application Security","Claude API integration","Context engineering","Eval & debugging","MCP Server Development","Model Optimization","Prompt Engineering"]},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/69048709-7ebe-4acf-ad2d-dfcd09754bff#credential","credentialCategory":"certification","name":"CyberOps Associate","url":"https://www.credly.com/badges/69048709-7ebe-4acf-ad2d-dfcd09754bff","identifier":"69048709-7ebe-4acf-ad2d-dfcd09754bff","dateCreated":"2022-07-13","image":"https://www.ashutosh887.in/images/badges/cyberops-associate.png","recognizedBy":{"@type":"Organization","name":"Cisco"},"competencyRequired":["Attack Methods","Computer Forensics","Cryptography","Cybersecurity","Data And Event Analysis","Endpoint Threat Analysis","Host-based Analysis","Incident Response","Malware Analysis","Network Attacks","Network Intrusion Analysis SecOps","SOC Metrics","Security Concepts","Security Monitoring","Security Policy","Security Procedures","Threat Detection"]},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/59c573d4-6dd6-4cea-b469-dc9bdc5ef335#credential","credentialCategory":"certification","name":"Introduction to Cybersecurity","url":"https://www.credly.com/badges/59c573d4-6dd6-4cea-b469-dc9bdc5ef335","identifier":"59c573d4-6dd6-4cea-b469-dc9bdc5ef335","dateCreated":"2022-07-03","image":"https://www.ashutosh887.in/images/badges/introduction-to-cybersecurity.png","recognizedBy":{"@type":"Organization","name":"Cisco"},"competencyRequired":["Cyber Best Practices","Cybersecurity","Network Vulnerabilities","Privacy And Data Confidentiality","Threat Detection"]},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/ffaee72b-bd73
1-4f49-8d31-9e9ae0613651#credential","credentialCategory":"certification","name":"Cybersecurity Fundamentals","url":"https://www.credly.com/badges/ffaee72b-bd73-4f49-8d31-9e9ae0613651","identifier":"ffaee72b-bd73-4f49-8d31-9e9ae0613651","dateCreated":"2022-03-28","image":"https://www.ashutosh887.in/images/badges/cybersecurity-fundamentals.png","recognizedBy":{"@type":"Organization","name":"IBM SkillsBuild"},"competencyRequired":["Cryptography","Cyber Attacks","Cyber Threat Analysis","Cyber Threat Intelligence","Cybersecurity","Cybersecurity Processes","Cybersecurity Risk Management","Incident Response","Information Security","Security Strategies","Social Engineering","Threat Analysis","Threat Detection","Vulnerability Management"]},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/4fe1d202-03a1-42ca-a8e8-7af7e00681d1#credential","credentialCategory":"certification","name":"CCNA: Introduction to Networks","url":"https://www.credly.com/badges/4fe1d202-03a1-42ca-a8e8-7af7e00681d1","identifier":"4fe1d202-03a1-42ca-a8e8-7af7e00681d1","dateCreated":"2022-01-14","image":"https://www.ashutosh887.in/images/badges/ccna-introduction-to-networks.png","recognizedBy":{"@type":"Organization","name":"Cisco"},"competencyRequired":["Ethernet","IP Subnetting","IP connectivity","IP services","IPv4 And IPv6 Addressing","Network Fundamentals","Security Fundamentals","Switching"]},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/e8ef4a61-8e5f-4250-bf4c-e8afc66f9bb3#credential","credentialCategory":"certification","name":"Introduction to Packet Tracer","url":"https://www.credly.com/badges/e8ef4a61-8e5f-4250-bf4c-e8afc66f9bb3","identifier":"e8ef4a61-8e5f-4250-bf4c-e8afc66f9bb3","dateCreated":"2022-01-13","image":"https://www.ashutosh887.in/images/badges/introduction-to-packet-tracer.png","recognizedBy":{"@type":"Organization","name":"Cisco"},"competencyRequired":["Cisco Packet Tracer","IoT Simulation","Network Simulation"]},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/84e485f2-a0f7-4582-ba27-07c38a0f8e4f#credential","credentialCategory":"certification","name":"AWS Academy Graduate - Cloud Foundations - Training Badge","url":"https://www.credly.com/badges/84e485f2-a0f7-4582-ba27-07c38a0f8e4f","identifier":"84e485f2-a0f7-4582-ba27-07c38a0f8e4f","dateCreated":"2021-12-25","image":"https://www.ashutosh887.in/images/badges/aws-academy-graduate-cloud-foundations.png","recognizedBy":{"@type":"Organization","name":"Amazon Web Services"},"competencyRequired":["AWS Architecture","AWS Cloud","AWS Core Services","AWS Pricing","AWS Support"]},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/f2586622-bbc5-4af4-93e3-50b31f9a41b6#credential","credentialCategory":"certification","name":"AWS Academy Graduate - Machine Learning Foundations - Training Badge","url":"https://www.credly.com/badges/f2586622-bbc5-4af4-93e3-50b31f9a41b6","identifier":"f2586622-bbc5-4af4-93e3-50b31f9a41b6","dateCreated":"2021-12-25","image":"https://www.ashutosh887.in/images/badges/aws-academy-graduate-machine-learning-foundations.png","recognizedBy":{"@type":"Organization","name":"Amazon Web Services"},"competencyRequired":["AWS","AWS Cloud Computing","Artificial Intelligence: Machine Learning","Machine Learning","Machine Learning (ML) Foundations"]},{"@type":"EducationalOccupationalCredential","@id":"https://www.credly.com/badges/87e3a099-36c5-456f-94ea-84068db07d4c#credential","credentialCategory":"certification","name":"Enterprise Design Thinking Practitioner","url":"https://www.credly.com/badges/87e3a099-36c5-456f-94ea-84068db07d4c","identifier":"87e3a099-36c5-456f-94ea-84068db07d4c","dateCreated":"2021-06-26","image":"https://www.ashutosh887.in/images/badges/enterprise-design-thinking-practitioner.png","recognizedBy":{"@type":"Organization","name":"IBM"},"competencyRequired":["Design","Empathy","Experience Design","Ideation","UX","User Experience","User Research","User-Centered Design","User-Centric"]}],"image":{"@type":"ImageObject","url":"https://www.ashutosh887.in/opengraph-image","width":1200,"height":630},"nationality":{"@type":"Country","name":"India"}},{"@context":"https://schema.org","@type":"WebSite","@id":"https://www.ashutosh887.in/#website","url":"https://www.ashutosh887.in","name":"Ashutosh Jha Portfolio","description":"Portfolio of Ashutosh Jha, an AI and full stack engineer. Agent systems, backends, and the cloud infrastru
1cture under them.","publisher":{"@id":"https://www.ashutosh887.in/#person"},"inLanguage":"en-IN","copyrightYear":2026,"creator":{"@id":"https://www.ashutosh887.in/#person"}},{"@context":"https://schema.org","@type":"ProfessionalService","@id":"https://www.ashutosh887.in/#service","name":"Ashutosh Jha - Software Engineering Services","description":"AI and full stack engineering: agent systems, RAG pipelines, product work, and the backends and cloud infrastructure under them. Available for full-time roles and consulting.","provider":{"@id":"https://www.ashutosh887.in/#person"},"address":{"@type":"PostalAddress","addressLocality":"Bengaluru","addressRegion":"Karnataka","addressCountry":"IN"},"areaServed":{"@type":"GeoCircle","geoMidpoint":{"@type":"GeoCoordinates","latitude":"12.9716","longitude":"77.5946"},"geoRadius":"50000"},"hasOfferCatalog":{"@type":"OfferCatalog","name":"Development Services","itemListElement":[{"@type":"Offer","itemOffered":{"@type":"Service","name":"AI Engineering","description":"LLM and agent systems, RAG pipelines, evals, and MCP integrations in Python and TypeScript"}},{"@type":"Offer","itemOffered":{"@type":"Service","name":"Full Stack Development","description":"Web applications end to end with Next.js, React, Node.js, FastAPI, and PostgreSQL"}},{"@type":"Offer","itemOffered":{"@type":"Service","name":"Cloud and Infrastructure","description":"Backends, data pipelines, and observability on AWS and Google Cloud, with Docker and Kubernetes"}},{"@type":"Offer","itemOffered":{"@type":"Service","name":"Web3 Development","description":"Smart contracts, Solana programs, and wallet integrations"}}]}},{"@context":"https://schema.org","@type":"ItemList","@id":"https://www.ashutosh887.in/#projects","name":"Projects by Ashutosh Jha","description":"Agent infrastru
1cture, sales and learning environments, prompt evolution and audio QC — including Stub (budget gate for agents, on npm), NeverLose (real-time buyer agent), FinQuery (OpenEnv for finance), Evolv (prompt DNA), WinterArc (offline-first habit tracker), and StudioCast (audio drama QC).","numberOfItems":32,"itemListElement":[{"@type":"ListItem","position":1,"item":{"@type":"SoftwareApplication","name":"Stub","description":"A drop-in budget gate for AI agents that spend real money. Covers paid APIs, x402 micropayments, and LLM tokens. One enforceable budget in front of the whole fleet, with an exact double-entry record of every agent's spend. Uses a reserve → pay → settle flow so irreversible payments fire exactly once, even under retries or crashes.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/stub","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":2,"item":{"@type":"SoftwareApplication","name":"Signet","description":"An identity and governance layer for AI agents. Every action is wrapped in a signed, verifiable envelope and policy gated before execution. Ships with Python and TypeScript SDKs plus MCP/A2A middleware for drop-in adoption across agent stacks.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/signet","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":3,"item":{"@type":"SoftwareApplication","name":"NeverLose","description":"An AI sales agent that works on hesitant buyers in real time. It reads 11 buyer signals and runs an escalating negotiation before the customer leaves. Two-sided: a customer-facing sales agent plus a merchant intelligence copilot on shared infrastructure. Finalist (Top 5 of 90+) at the Pine Labs AI Hackathon.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/neverlose","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":4,"item":{"@type":"SoftwareApplication","name":"FinQuery","description":"An OpenEnv-compatible reinforcement learning environment for financial reasoning. Each reset procedurally generates a verifiable finance question. The agent decides which data to fetch and how to combine it, earning dense per-step rewards. Covers 25 companies across 7 sectors over 9 years (2017-2025).","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/finquery","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":5,"item":{"@type":"SoftwareApplication","name":"Evolv","description":"Prompt evolution as genetic sequences. Evolv extracts a DNA fingerprint from every prompt, clusters them semantically with embeddings, synthesizes templates from the clusters, and tracks each mutation and its lineage. Won 1st prize at the Portkey AI Builder Challenge.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/evolv","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":6,"item":{"@type":"SoftwareApplication","name":"WinterArc","description":"An offline-first habit tracker for a fixed run of days. October 1 through December 31 is the winter arc, but you can set any dates. All habit data stays in your browser. No account, no sync, no backend. Ships as a PWA you can add to your home screen, with a warm-up window, rest days, a grid for the full run, per-habit rings and streaks, local reminders, and JSON and CSV export.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/winterarc","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":7,"item":{"@type":"SoftwareApplication","name":"saathi","description":"If you can say it, it gets done. Saathi is a voice-first workflow engine where a JSON file runs as a spoken conversation in Kannada, Hindi or English. Talk a form into existence one question at a time, or bridge a call between two people who do not share a language. A resolver cascade handles closed sets and rules for free before calling a model, and the engine refuses to guess below 0.75 confidence.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/saathi","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":8,"item":{"@type":"SoftwareApplication","name":"Request Layer","description":"Three-tier cache, coalescer, and dollar-aware rate limits for the agent fleet. Request Layer sits between Kong and the Nasiko agent fleet. It adds L1 exact, L2 semantic, and L3 router-decision caching, collapses 200 concurrent duplicates into one origin call with an in-flight coalescer, and gates traffic with a per-agent token-bucket, rolling dollar-per-minute meter, and three-lane priority queue. Observable via admin REST and SSE with Phoenix cache.hit spans.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/request-layer","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":9,"item":{"@type":"SoftwareApplication","name":"ClickLiv","description":"Real-time foreground-only concurrency for SonyLIV streaming telemetry, on ClickHouse. ClickLiv ingests 7 million session events into ClickHouse, reconstructs truly active playback intervals, and rolls them to one row per session minute. It serves peak and average concurrency at any grain and filter combination from that rollup, with incremental handling of still-open sessions. Same numbers power the web dashboard, conversational surface, and MCP server through one budgeted read-only role.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/clickliv","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":10,"item":{"@type":"SoftwareApplication","name":"StudioCast","description":"The quality layer for AI audio drama. Paste a chapter and StudioCast directs it into a multi-voice scene, then listens to its own render. It re-transcribes the audio, checks emotion two independent ways, measures pacing and loudness, and holds lines that miss their direction.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/studiocast","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":11,"item":{"@type":"SoftwareApplication","name":"verdex","description":"Image-grounded adjudication for damage claims. Verdex looks at the photos for a claim and decides what the pixels show. It treats the chat and text inside images as untrusted data and returns supported, contradicted, or not enough information. Images decide. History only adds a risk flag.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/verdex","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":12,"item":{"@type":"SoftwareApplication","name":"Plumb","description":"Signer-side security for Solana multisigs. Plumb is a browser extension that sits on the Squads V4 approval modal and shows what you are about to sign in plain English. It decodes durable-nonce replay windows, flags owner-mismatched nonce accounts, diffs account and authority changes via Surfpool simulation, and diffs BPF bytecode for program upgrades. Read-only at the signer interface, it never signs or modifies the transaction.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/plumb","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":13,"item":{"@type":"SoftwareApplication","name":"Darwin","description":"Self
1-evolving AI agents via git-native natural selection. Darwin keeps agent config in git and uses the history as the evolution engine. A subject agent tries a task, a reviewer scores it, and an orchestrator branches, mutates SOUL.md and RULES.md, validates, and merges only the fitter version. Every generation is a commit, every trait is traceable with blame and diff.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/darwin","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":14,"item":{"@type":"SoftwareApplication","name":"ClawGuard","description":"Local AI that safely touches the world, with zero token exposure. Core reasoning runs locally. A cloud intermediary exchanges scoped tokens through Auth0 Token Vault, so OAuth tokens never reach the device. Every external call is gated by permission preview, offline queue, anomaly shield, and CIBA step-up, with a live SSE audit trail and one-click revoke in under two seconds.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/clawguard","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":15,"item":{"@type":"SoftwareApplication","name":"Stoq","description":"The AI that makes 13.7 million kiranas think, stock, buy, lend, and compete as one. Stoq is a coordination layer on Paytm Soundbox that turns isolated kiranas into a mesh. It infers stock from supplier payments, pools demand for 14 to 20 percent bulk savings, forecasts cash flow and routes mesh credit at 6 to 8 percent APR, and handles GST compliance. Voice-first in 11 languages, with Soundbox and WhatsApp briefings.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/stoq","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":16,"item":{"@type":"SoftwareApplication","name":"FaultLine","description":"Root-cause analysis for AI decisions. FaultLine instruments an agent with an SDK, captures every step to an ingest API, and a BullMQ worker turns the trace into an incident report. It builds a timeline, names the root cause and contributing factors, and lists fixes with evidence from the trace.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/faultline","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":17,"item":{"@type":"SoftwareApplication","name":"FeelTheWeb","description":"An AI-powered plugin that turns what is on screen into haptic patterns. FeelTheWeb is a plugin for Logitech MX hardware. Claude Haiku 4.5 maps the page every 1 to 2 seconds, then the mouse plays distinct patterns for links, buttons, text, images, and empty space, the Creative Console shows a 3 by 3 spatial map, and voice AI narrates on demand.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/feeltheweb","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":18,"item":{"@type":"SoftwareApplication","name":"moodcast","description":"Turn any text into emotionally expressive audio with ambient soundscapes. Moodcast is a Moltbot/OpenClaw skill on ElevenLabs v3. It detects emotion in text and inserts audio tags to shape delivery, then renders speech with a matching ambient soundscape from the Sound Effects API. Mood presets map to voices, long text is split automatically, and the CLI can save to file or show the enhanced text before generation.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/moodcast","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":19,"item":{"@type":"SoftwareApplication","name":"BridgeRadar","description":"See what could go wrong before you bridge. BridgeRadar simulates a bridge transaction before you sign it. It pulls every LI.FI route for the pair, scores each one for security, liquidity and failure rate, and shows expected versus worst case outcomes so you pick with eyes open.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/bridgeradar","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":20,"item":{"@type":"SoftwareApplication","name":"PayFlow","description":"Visual programmable payment workflows with MNEE. PayFlow lets you build payment logic on a canvas and ship it on Ethereum Sepolia with the MNEE token. Create milestone releases, revenue splits, and multi-party approvals that pause, resume, and deploy on the spot. A FlowFactory deploys each flow as its own contract.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/payflow","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":21,"item":{"@type":"SoftwareApplication","name":"AlivePing","description":"Your last-mile personal safety system, built on Solana. AlivePing watches a check-in window and fires if you miss it, with a panic button for immediate help. Every session is written to Solana testnet as tamper-proof proof, alerts go out over WhatsApp via the Meta Business API, and location and events stream in real time through Confluent.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/aliveping","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":22,"item":{"@type":"SoftwareApplication","name":"SafeVoice","description":"AI-powered legal evidence documentation for victims of abuse. SafeVoice opens as a decoy meditation app and reveals its real flow only after long-press and PIN. A victim speaks, the app transcribes, asks gentle follow-ups, and builds a 
1secure evidence timeline with escalation detection. Calming guidance is voiced with ElevenLabs, reasoning runs on Gemini, and exits are instant for high-risk environments.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/safevoice","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":23,"item":{"@type":"SoftwareApplication","name":"ShotLock","description":"Deterministic creative control for AI-generated visuals. ShotLock is a visual generation tool on Bria FIBO where you lock camera and composition and then iterate on lighting, color, and mood. A proof grid shows variations side by side so teams keep outputs consistent across a creative workflow. Built on Next.js, Prisma, and MongoDB.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/shotlock","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":24,"item":{"@type":"SoftwareApplication","name":"CareerFit","description":"We do not prepare you. We qualify you. CareerFit reads a resume from PDF, DOCX, or image, extracts skills and level, and scores hire probability against live market demand. It shows gaps, salary ranges, and trends, then returns a roadmap of projects with impact estimates, plus role-specific mock interviews with feedback and tracked history.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/careerfit","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":25,"item":{"@type":"SoftwareApplication","name":"LaunchKit","description":"Ship fast. Get customers faster. LaunchKit reads any website, infers the ideal customer profile, and turns it into a GTM plan. It writes the messaging framework and the execution checklist so founders move from analysis to outreach without starting from a blank page.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/launchkit","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":26,"item":{"@type":"SoftwareApplication","name":"CivicLens","description":"Bringing clarity to public services for everyone. CivicLens is a chat interface for government schemes and civic processes. Ask in plain English, get streaming answers on eligibility and how to apply, with entity extraction and query classification underneath. Upload a PDF to ground the answer, crawl portals and parse PDFs via Kestra workflows, and optionally fine-tune with a small Oumi dataset.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/civiclens","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":27,"item":{"@type":"SoftwareApplication","name":"DevBuzz","description":"Where developers build, share, and grow. DevBuzz is a community platform with OTP login, session cookies, and a feed with infinite scroll. Posts support threaded nested comments with single upvote per user, inline replies, and toast feedback. Built on Next.js App Router, Prisma and Neon Postgres, with Redux Toolkit for state and Resend for email.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/devbuzz","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":28,"item":{"@type":"SoftwareApplication","name":"PolkaSafe","description":"Multisig and treasury infrastructure for Polkadot. PolkaSafe ran the primary multisig for Polkadot, Kusama, Astar, Aleph Zero and EVM chains, with peak $300M under management. Built on Substrate's multisig and proxy pallets, it handled N-of-M signing, batch extrinsics, on-chain treasury votes, and hardware signing via Polkadot Vault. I worked on the UI with Polkadot.js and Firebase Auth. Archived May 2026.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/polkasafe","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":29,"item":{"@type":"SoftwareApplication","name":"Trance","description":"An online music streaming web application. Trance is a streaming app focused on shuffling and playlist curation. Browse artists, build playlists, and play through a custom player built on Next.js and Prisma. Version 1 is deprecated while version 2 is in development.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/trance","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":30,"item":{"@type":"SoftwareApplication","name":"ShoppersEnd","de
1scription":"Gamified e-commerce. ShoppersEnd is a full stack store where discounts are earned through achievements and loyalty points. It handles cart, checkout, order tracking, and personalized recommendations, with a React and Material UI frontend and a Node, Express, and MongoDB backend with Stripe.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/shoppersend","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":31,"item":{"@type":"SoftwareApplication","name":"depextract","description":"A convenient CLI tool for dependency extraction. Point depextract at a package.json and it lists production and dev dependencies, then generates an install script for npm, yarn, or pnpm. Run with npx depextract with no install, pick the location of the package.json, and the script lands in scripts.sh.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/depextract","author":{"@id":"https://www.ashutosh887.in/#person"}}},{"@type":"ListItem","position":32,"item":{"@type":"SoftwareApplication","name":"ethsapien","description":"Decentralized AI-powered credentialing for on-chain identity and reputation. Ethsapien issues verifiable credentials on chain for identity and reputation. Cairo and Solidity contracts manage issuance and verification, with a Next.js app for handling credentials. Built as an early experiment in AI-assisted credentialing.","operatingSystem":"Web","url":"https://www.ashutosh887.in/projects/ethsapien","author":{"@id":"https://www.ashutosh887.in/#person"}}}]}]}</script>
1<script src="/_next/static/immutable/chunks/0c0hxoamwjsbw.js" noModule=""></script>
1</head><body class="bg-canvas text-ink font-sans antialiased"><div hidden=""><!--$--><!--/$--></div><a href="#main-content" class="sr-only focus:not-sr-only focus:fixed focus:left-4 focus:top-4 focus:z-200 focus:inline-flex focus:items-center focus:rounded-full focus:bg-accent focus:px-5 focus:py-2.5 focus:text-sm focus:font-semibold focus:text-accent-contrast focus:shadow-xl focus:shadow-black/40 focus:outline-none focus:ring-2 focus:ring-white/60">Skip to content</a><header class="fixed inset-x-0 top-4 z-50 hidden md:top-5 lg:block" style="opacity:0;transform:translateY(-64px)"><div class="mx-auto flex w-full max-w-6xl items-center justify-between px-6 md:px-8"><div style="opacity:0;transform:translateX(-16px) scale(0.6)"><a aria-label="Back to home" class="nav-aura block h-12 w-12 rounded-full shadow-lg shadow-black/40 transition-transform duration-200 hover:scale-105 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent " href="/"><span class="relative block h-full w-full overflow-hidden rounded-full"><img alt="" aria-hidden="true" loading="lazy" decoding="async" data-nimg="fill" class="object-cover object-top" style="position:absolute;height:100%;width:100%;left:0;top:0;right:0;bottom:0;color:transparent" sizes="48px" srcSet="/_next/image?url=%2Fme.jpg&amp;w=16&amp;q=75 16w, /_next/image?url=%2Fme.jpg&amp;w=32&amp;q=75 32w, /_next/image?url=%2Fme.jpg&amp;w=48&amp;q=75 48w, /_next/image?url=%2Fme.jpg&amp;w=64&amp;q=75 64w, /_next/image?url=%2Fme.jpg&amp;w=96&amp;q=75 96w, /_next/image?url=%2Fme.jpg&amp;w=128&amp;q=75 128w, /_next/image?url=%2Fme.jpg&amp;w=256&amp;q=75 256w, /_next/image?url=%2Fme.jpg&amp;w=384&amp;q=75 384w, /_next/image?url=%2Fme.jpg&amp;w=640&amp;q=75 640w, /_next/image?url=%2Fme.jpg&amp;w=750&amp;q=75 750w, /_next/image?url=%2Fme.jpg&amp;w=828&amp;q=75 828w, /_next/image?url=%2Fme.jpg&amp;w=1080&amp;q=75 1080w, /_next/image?url=%2Fme.jpg&amp;w=1200&amp;q=75 1200w, /_next/image?url=%2Fme.jpg&amp;w=1920&amp;q=75 1920w, /_next/image?url=%2Fme.jpg&amp;w=2048&amp;q=75 2048w, /_next/image?url=%2Fme.jpg&amp;w=3840&amp;q=75 3840w" src="/_next/image?url=%2Fme.jpg&amp;w=3840&amp;q=75"/></span></a></div><div class="ml-auto nav-aura rounded-full bg-[rgb(var(--canvas)/0.82)] shadow-xl shadow-black/40 backdrop-blur-2xl backdrop-saturate-150 "><div class="relative z-2 flex items-center gap-1 rounded-full p-1.5"><nav aria-label="Primary" class="flex items-center gap-0.5"><a style="--la:#818cf8" class="inline-flex h-9 items-center justify-center rounded-full px-3.5 text-[13px] font-medium transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent nav-item relative " href="/experience"><span class="nav-item-label relative">Experience</span></a><a style="--la:#22d3ee" class="inline-flex h-9 items-center justify-center rounded-full px-3.5 text-[13px] font-medium transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent nav-item relative " href="/projects"><span class="nav-item-label relative">Projects</span></a><a aria-current="page" style="--la:#fb7185" class="inline-flex h-9 items-center justify-center rounded-full px-3.5 text-[13px] font-medium transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent nav-item relative nav-active" href="/writing"><span aria-hidden="true" class="absolute inset-0 rounded-full bg-white/8"></span><span class="nav-item-label relative">Writing</span></a></nav><button type="button" aria-label="Search (Command K)" class="inline-flex h-9 items-center justify-center rounded-full px-3.5 text-[13px] font-medium transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent shrink-0 gap-2 bg-white/4! px-3.5 text-faint hover:bg-white/9! hover:text-ink"><div class="inline-flex items-center justify-center"><svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><g opacity="1" style="transform:none;transform-origin:50% 50%;transform-box:fill-box"><circle cx="11" cy="11" r="8"></circle><path d="m21 21-4.34-4.34"></path></g></svg></div><span aria-hidden="true" class="text-[13px] font-medium leading-none tracking-[0.01em]"><span class="align-[-0.06em] text-[15px] leading-none">⌘</span>K</span></button><span aria-hidden="true" class="mx-0.5 h-5 w-px bg-hairline-strong"></span><div class="flex items-center gap-0.5"><a href="https://github.com/ashutosh887" target="_blank" rel="noreferrer noopener" aria-label="GitHub" class="inline-flex items-center justify-center rounded-full text-muted transition-colors duration-200 hover:text-accent focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent h-9 w-9" tabindex="0"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 496 512" height="14" width="14" xmlns="http://www.w3.org/2000/svg"><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"></path></svg></a><a href="https://www.linkedin.com/in/ashutosh887" target="_blank" rel="noreferrer noopener" aria-label="LinkedIn" class="inline-flex items-center justify-center rounded-full text-muted transition-colors duration-200 hover:text-accent focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent h-9 w-9" tabindex="0"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 448 512" height="14" width="14" xmlns="http://www.w3.org/2000/svg"><path d="M416 32H31.9C14.3 32 0 46.5 0 64.3v383.4C0 465.5 14.3 480 31.9 480H416c17.6 0 32-14.5 32-32.3V64.3c0-17.8-14.4-32.3-32-32.3zM135.4 416H69V202.2h66.5V416zm-33.2-243c-21.3 0-38.5-17.3-38.5-38.5S80.9 96 102.2 96c21.2 0 38.5 17.3 38.5 38.5 0 21.3-17.2 38.5-38.5 38.5zm282.1 243h-66.4V312c0-24.8-.5-56.7-34.5-56.7-34.6 0-39.9 27-39.9 54.9V416h-66.4V202.2h63.7v29.2h.9c8.9-16.8 30.6-34.5 62.9-34.5 67.2 0 79.7 44.3 79.7 101.9V416z"></path></svg></a><a href="https://x.com/ashutosh887_" target="_blank" rel="noreferrer noopener" aria-label="Twitter/X" class="inline-flex items-center justify-center rounded-full text-muted transition-colors duration-200 hover:text-accent focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent h-9 w-9" tabindex="0"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 512 512" height="14" width="14" xmlns="http://www.w3.org/2000/svg"><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"></path></svg></a><a href="https://instagram.com/ashutosh887_" target="_blank" rel="noreferrer noopener" aria-label="Instagram" class="inline-flex items-center justify-center rounded-full text-muted transition-colors duration-200 hover:text-accent focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent h-9 w-9" tabindex="0"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 448 512" height="14" width="14" xmlns="http://www.w3.org/2000/svg"><path d="M224.1 141c-63.6 0-114.9 51.3-114.9 114.9s51.3 114.9 114.9 114.9S339 319.5 339 255.9 287.7 141 224.1 141zm0 189.6c-41.1 0-74.7-33.5-74.7-74.7s33.5-74.7 74.7-74.7 74.7 33.5 74.7 74.7-33.6 74.7-74.7 74.7zm146.4-194.3c0 14.9-12 26.8-26.8 26.8-14.9 0-26.8-12-26.8-26.8s12-26.8 26.8-26.8 26.8 12 26.8 26.8zm76.1 27.2c-1.7-35.9-9.9-67.7-36.2-93.9-26.2-26.2-58-34.4-93.9-36.2-37-2.1-147.9-2.1-184.9 0-35.8 1.7-67.6 9.9-93.9 36.1s-34.4 58-36.2 93.9c-2.1 37-2.1 147.9 0 184.9 1.7 35.9 9.9 67.7 36.2 93.9s58 34.4 93.9 36.2c37 2.1 147.9 2.1 184.9 0 35.9-1.7 67.7-9.9 93.9-36.2 26.2-26.2 34.4-58 36.2-93.9 2.1-37 2.1-147.8 0-184.8zM398.8 388c-7.8 19.6-22.9 34.7-42.6 42.6-29.5 11.7-99.5 9-132.1 9s-102.7 2.6-132.1-9c-19.6-7.8-34.7-22.9-42.6-42.6-11.7-29.5-9-99.5-9-132.1s-2.6-102.7 9-132.1c7.8-19.6 22.9-34.7 42.6-42.6 29.5-11.7 99.5-9 132.1-9s102.7-2.6 132.1 9c19.6 7.8 34.7 22.9 42.6 42.6 11.7 29.5 9 99.5 9 132.1s2.7 102.7-9 132.1z"></path></svg></a><a href="mailto:[email protected]?subject=Hello%20from%20Portfolio&amp;
1body=Hi%20Ashutosh,%20I%20found%20your%20portfolio%20and%20would%20like%20to%20connect." target="_blank" rel="noreferrer noopener" aria-label="Email" class="inline-flex items-center justify-center rounded-full text-muted transition-colors duration-200 hover:text-accent focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent h-9 w-9" tabindex="0"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 512 512" height="14" width="14" xmlns="http://www.w3.org/2000/svg"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"></path></svg></a></div></div></div></div></header><div class="fixed inset-x-0 bottom-0 z-70 pb-[env(safe-area-inset-bottom)] lg:hidden"><div aria-hidden="true" class="pointer-events-none absolute inset-x-0 bottom-0 h-28" style="background:linear-gradient(to top, rgb(var(--canvas)) 0%, rgb(var(--canvas) / 0.92) 40%, transparent 100%)"></div><nav aria-label="Primary" class="nav-aura relative mx-4 mb-4 max-w-md rounded-full sm:mx-auto bg-[rgb(var(--canvas)/0.85)] shadow-xl shadow-black/40 backdrop-blur-2xl backdrop-saturate-150 "><div class="relative z-2 flex items-center gap-1 rounded-full p-1.5"><a style="--la:rgb(var(--accent))" class="relative flex h-12 min-w-0 flex-1 flex-col items-center justify-center gap-1 rounded-full transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent text-faint" href="/"><span class="relative flex h-[18px] w-[18px] items-center justify-center"><div class="inline-flex items-center justify-center"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><g style="transform-box:view-box;transform:none;transform-origin:12px 21px 0"><path d="M3 10a2 2 0 0 1 .709-1.528l7-5.999a2 2 0 0 1 2.582 0l7 5.999A2 2 0 0 1 21 10"></path><path d="M21 10v9a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2v-9"></path><path d="M15 21v-8a1 1 0 0 0-1-1h-4a1 1 0 0 0-1 1v8" opacity="1" style="transform-box:view-box;transform:none;transform-origin:12px 21px 0"></path></g></svg></div></span><span class="relative text-[11px] leading-none tracking-tight">Home</span></a><a style="--la:#22d3ee" class="relative flex h-12 min-w-0 flex-1 flex-col items-center justify-center gap-1 rounded-full transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent text-faint" href="/projects"><span class="relative flex h-[18px] w-[18px] items-center justify-center"><div class="inline-flex items-center justify-center"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="transform:none"><path d="M12.83 2.18a2 2 0 0 0-1.66 0L2.6 6.08a1 1 0 0 0 0 1.83l8.58 3.91a2 2 0 0 0 1.66 0l8.58-3.9a1 1 0 0 0 0-1.83z" opacity="1" style="transform:none;transform-origin:50% 50%;transform-box:fill-box"></path><path d="M2 12a1 1 0 0 0 .58.91l8.6 3.91a2 2 0 0 0 1.65 0l8.58-3.9A1 1 0 0 0 22 12" opacity="1" style="transform:none;transform-origin:50% 50%;transform-box:fill-box"></path><path d="M2 17a1 1 0 0 0 .58.91l8.6 3.91a2 2 0 0 0 1.65 0l8.58-3.9A1 1 0 0 0 22 17" opacity="1" style="transform:none;transform-origin:50% 50%;transform-box:fill-box"></path></svg></div></span><span class="relative text-[11px] leading-none tracking-tight">Projects</span></a><a aria-current="page" style="--la:#fb7185" class="relative flex h-12 min-w-0 flex-1 flex-col items-center justify-center gap-1 rounded-full transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent text-[var(--la)]" href="/writing"><span aria-hidden="true" class="absolute inset-0 rounded-full bg-white/8"></span><span class="relative flex h-[18px] w-[18px] items-center justify-center"><div class="inline-flex items-center justify-center"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><g style="transform-box:view-box;transform:none;transform-origin:2.15px 21.85px 0"><path d="M21.174 6.812a1 1 0 0 0-3.986-3.987L3.842 16.174a2 2 0 0 0-.5.83l-1.321 4.352a.5.5 0 0 0 .623.622l4.353-1.32a2 2 0 0 0 .83-.497z"></path><path d="m15 5 4 4"></path></g></svg></div></span><span class="relative text-[11px] leading-none tracking-tight">Writing</span></a><button type="button" aria-label="Search" class="relative flex h-12 min-w-0 flex-1 flex-col items-center justify-center gap-1 rounded-full transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent text-faint"><span class="relative flex h-[18px] w-[18px] items-center justify-center"><div class="inline-flex items-center justify-center"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><g opacity="1" style="transform:none;transform-origin:50% 50%;transform-box:fill-box"><circle cx="11" cy="11" r="8"></circle><path d="m21 21-4.34-4.34"></path></g></svg></div></span><span class="relative text-[11px] leading-none tracking-tight">Search</span></button><button type="button" aria-expanded="false" aria-controls="site-menu-sheet" aria-label="Open menu" class="relative flex h-12 min-w-0 flex-1 flex-col items-center justify-center gap-1 rounded-full transition-colors duration-200 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-accent text-faint"><span class="relative flex h-[18px] w-[18px] items-center justify-center"><div class="inline-flex items-center justify-center"><svg xmlns="http://www.w3.org/2000/svg" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M4 6h16" style="transform-origin:50% 50%;transform:none;transform-box:fill-box"></path><path d="M4 12h16" style="transform-origin:50% 50%;transform:none;transform-box:fill-box"></path><path d="M4 18h16" style="transform-origin:50% 50%;transform:none;transform-box:fill-box"></path></svg></div></span><span class="relative text-[11px] leading-none tracking-tight">Menu</span></button></div></nav></div><div aria-hidden="true" class="template-curtain pointer-events-none fixed inset-0 z-70 bg-canvas"></div><div class="template-content"><div aria-hidden="true" class="pointer-events-none fixed inset-0 z-0"><canvas aria-hidden="true" class="h-full w-full"></canvas><div class="absolute inset-0" style="background:radial-gradient(60% 50% at 75% 10%, rgb(var(--accent) / 0.05), transparent 70%)"></div><div class="absolute inset-0" style="background:radial-gradient(45% 40% at 12% 88%, rgb(var(--accent) / 0.06), transparent 70%)"></div></div><div class="relative z-10 flex min-h-svh flex-col">
1<main id="main-content" class="flex-1"><div class="shell page-pad">
1<script type="application/ld+json">{"@context":"https://schema.org","@type":"BlogPosting","@id":"https://www.ashutosh887.in/writing/evals-are-the-product/#post","headline":"Evals are the product","description":"Ship an LLM feature and the eval suite becomes the spec, whether you meant it to or not. Write it like one from the start.","datePublished":"2026-06-12","dateModified":"2026-06-12","articleSection":"Evals","keywords":"ai, llm, evals, machine-learning","image":"https://www.ashutosh887.in/writing/evals-are-the-product/opengraph-image","inLanguage":"en-IN","url":"https://www.ashutosh887.in/writing/evals-are-the-product","mainEntityOfPage":{"@type":"WebPage","@id":"https://www.ashutosh887.in/writing/evals-are-the-product"},"author":{"@id":"https://www.ashutosh887.in/#person"},"publisher":{"@id":"https://www.ashutosh887.in/#person"},"isPartOf":{"@id":"https://www.ashutosh887.in/#website"}}</script>
1<script type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://www.ashutosh887.in"},{"@type":"ListItem","position":2,"name":"Writing","item":"https://www.ashutosh887.in/writing"},{"@type":"ListItem","position":3,"name":"Evals are the product","item":"https://www.ashutosh887.in/writing/evals-are-the-product"}]}</script>
1<article><a class="ghost-button" href="/writing"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-left h-4 w-4" aria-hidden="true"><path d="m12 19-7-7 7-7"></path><path d="M19 12H5"></path></svg>All writing</a><header class="mt-9 border-b border-hairline pb-8 sm:mt-12 sm:pb-10"><div class="flex flex-wrap items-center gap-2"><span class="chip px-3.5 py-1.5 text-sm border-accent/30 text-accent">Evals</span><span class="chip px-3.5 py-1.5 text-sm">12 Jun 2026</span><span class="chip px-3.5 py-1.5 text-sm">2 min read</span></div><h1 class="mt-5 font-display text-4xl font-semibold leading-[1.05] tracking-tight text-balance text-ink md:text-5xl">Evals are the product</h1></header><div class="post-body"><p>Every LLM project hits the point where the prompt stops being the artifact you care about and the eval suite takes its place. Rewriting a prompt takes five minutes. Knowing whether the rewrite was better takes far longer, and staring harder at the outputs does not close that gap. The evals are the only thing standing between &#39;feels better on the three examples I tried&#39; and &#39;is better across the cases that matter.&#39;</p>
2<p>Most teams write their evals once, watch them go green, and never look again. Unit tests survive that treatment. Evals do not, because LLM behavior drifts with every model bump, prompt tweak, and retrieval change, and a stale eval set stops measuring the thing you actually ship. I have had better luck treating the set as a living spec. Every bug report becomes a case. Every regression becomes a case. The suite grows toward the real distribution of how the system gets used, which is the only distribution worth scoring against.</p>
3<p>Graders are where this gets hard. Exact-match works for a narrow slice of tasks. Everything else leaves you two options. A rubric that an LLM applies, or a human reading the outputs. LLM-as-judge scales, and it also inherits the same biases as the system under test, which is a real problem rather than a footnote. So I anchor the judge against a small human-labeled set first. If it disagrees with people there, it has no business scoring thousands of cases.</p>
4<p>The payoff is speed. Once the suite reflects reality you can refactor a pipeline hard, because the evals tell you within minutes what you broke. That is the whole advantage. A team that can answer &#39;did that change help?&#39; with evidence will outrun a team trading prompt tricks, and it will not be close.</p>
5<p>Here is the rule I hold to. Write the eval before the feature feels done, not after it breaks in production.</p>
6</div><footer class="mt-10 border-t border-hairline pt-8 sm:mt-14"><a class="ghost-button" href="/writing"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-left h-4 w-4" aria-hidden="true"><path d="m12 19-7-7 7-7"></path><path d="M19 12H5"></path></svg>All writing</a></footer></article></div></main><footer class="border-t border-hairline"><div class="shell mx-auto flex w-full max-w-6xl flex-col items-center justify-between gap-3 py-6 pb-24 sm:flex-row lg:pb-6"><div class="flex flex-col gap-1"><p class="mono-xs uppercase tracking-[0.14em] text-faint">© <span>2026</span> <!-- -->Ashutosh Jha</p></div><div class="flex flex-col items-center gap-3 sm:flex-row"><div class="flex items-center gap-3"><a class="text-sm text-muted transition-colors duration-150 hover:text-ink" href="/community">Community</a><span aria-hidden="true" class="h-4 w-px bg-hairline-strong"></span><a class="text-sm text-muted transition-colors duration-150 hover:text-ink" href="/contact">Get in touch</a></div><span aria-hidden="true" class="hidden h-4 w-px bg-hairline-strong sm:block"></span><div class="flex items-center gap-3"><a href="https://github.com/ashutosh887" target="_blank" rel="noreferrer noopener" aria-label="GitHub profile" class="relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[&#x27;&#x27;] transition-[color] duration-150 hover:text-ink"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 496 512" style="color:currentColor" aria-hidden="true" height="18" width="18" xmlns="http://www.w3.org/2000/svg"><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"></path></svg></a><a href="https://www.linkedin.com/in/ashutosh887" target="_blank" rel="noreferrer noopener" aria-label="LinkedIn profile" class="relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[&#x27;&#x27;] transition-[color] duration-150 hover:text-ink"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 448 512" style="color:currentColor" aria-hidden="true" height="18" width="18" xmlns="http://www.w3.org/2000/svg"><path d="M416 32H31.9C14.3 32 0 46.5 0 64.3v383.4C0 465.5 14.3 480 31.9 480H416c17.6 0 32-14.5 32-32.3V64.3c0-17.8-14.4-32.3-32-32.3zM135.4 416H69V202.2h66.5V416zm-33.2-243c-21.3 0-38.5-17.3-38.5-38.5S80.9 96 102.2 96c21.2 0 38.5 17.3 38.5 38.5 0 21.3-17.2 38.5-38.5 38.5zm282.1 243h-66.4V312c0-24.8-.5-56.7-34.5-56.7-34.6 0-39.9 27-39.9 54.9V416h-66.4V202.2h63.7v29.2h.9c8.9-16.8 30.6-34.5 62.9-34.5 67.2 0 79.7 44.3 79.7 101.9V416z"></path></svg></a><a href="https://x.com/ashutosh887_" target="_blank" rel="noreferrer noopener" aria-label="X (Twitter) profile" class="relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[&#x27;&#x27;] transition-[color] duration-150 hover:text-ink"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 512 512" style="color:currentColor" aria-hidden="true" height="18" width="18" xmlns="http://www.w3.org/2000/svg"><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"></path></svg></a><a href="https://instagram.com/ashutosh887_" target="_blank" rel="noreferrer noopener" aria-label="Instagram profile" class="relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[&#x27;&#x27;] transition-[color] duration-150 hover:text-ink"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 448 512" style="color:currentColor" aria-hidden="true" height="18" width="18" xmlns="http://www.w3.org/2000/svg"><path d="M224.1 141c-63.6 0-114.9 51.3-114.9 114.9s51.3 114.9 114.9 114.9S339 319.5 339 255.9 287.7 141 224.1 141zm0 189.6c-41.1 0-74.7-33.5-74.7-74.7s33.5-74.7 74.7-74.7 74.7 33.5 74.7 74.7-33.6 74.7-74.7 74.7zm146.4-194.3c0 14.9-12 26.8-26.8 26.8-14.9 0-26.8-12-26.8-26.8s12-26.8 26.8-26.8 26.8 12 26.8 26.8zm76.1 27.2c-1.7-35.9-9.9-67.7-36.2-93.9-26.2-26.2-58-34.4-93.9-36.2-37-2.1-147.9-2.1-184.9 0-35.8 1.7-67.6 9.9-93.9 36.1s-34.4 58-36.2 93.9c-2.1 37-2.1 147.9 0 184.9 1.7 35.9 9.9 67.7 36.2 93.9s58 34.4 93.9 36.2c37 2.1 147.9 2.1 184.9 0 35.9-1.7 67.7-9.9 93.9-36.2 26.2-26.2 34.4-58 36.2-93.9 2.1-37 2.1-147.8 0-184.8zM398.8 388c-7.8 19.6-22.9 34.7-42.6 42.6-29.5 11.7-99.5 9-132.1 9s-102.7 2.6-132.1-9c-19.6-7.8-34.7-22.9-42.6-42.6-11.7-29.5-9-99.5-9-132.1s-2.6-102.7 9-132.1c7.8-19.6 22.9-34.7 42.6-42.6 29.5-11.7 99.5-9 132.1-9s102.7-2.6 132.1 9c19.6 7.8 34.7 22.9 42.6 42.6 11.7 29.5 9 99.5 9 132.1s2.7 102.7-9 132.1z"></path></svg></a><a href="mailto:[email protected]?subject=Hello%20from%20Portfolio&amp;
6body=Hi%20Ashutosh,%20I%20found%20your%20portfolio%20and%20would%20like%20to%20connect." target="_blank" rel="noreferrer noopener" aria-label="Email Ashutosh" class="relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[&#x27;&#x27;] transition-[color] duration-150 hover:text-ink"><svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 512 512" style="color:currentColor" aria-hidden="true" height="18" width="18" xmlns="http://www.w3.org/2000/svg"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"></path></svg></a><a href="/feed.xml" class="relative text-faint transition-colors duration-150 hover:text-ink before:absolute before:-inset-3 before:rounded-full before:content-[&#x27;&#x27;]" aria-label="RSS feed"><svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M4 11a9 9 0 0 1 9 9"></path><path d="M4 4a16 16 0 0 1 16 16"></path><circle cx="5" cy="19" r="1"></circle></svg></a></div></div></div></footer></div><!--$--><!--/$--></div>
6<script src="/_next/static/immutable/chunks/2belr3pe9fbiz.js" id="_R_" async=""></script>
6<script>(self.__next_f=self.__next_f||[]).push([0])</script>
6<script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\n9:I[68027,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\"],\"default\",1]\n:HL[\"/_next/static/immutable/chunks/2l4hswa-ubkpn.css\",\"style\"]\n:HL[\"/_next/static/immutable/media/017d9bea37084d9b-s.p.2fl0vhx7oyatw.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/_next/static/immutable/media/797e433ab948586e-s.p.1v5bejj26fx9h.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n:HL[\"/_next/static/immutable/media/caa3a2e1cccd8315-s.p.0zr6hhvz-h9nw.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:T7ba4,{\"@context\":\"https://schema.org\",\"@graph\":[{\"@context\":\"https://schema.org\",\"@type\":\"Person\",\"@id\":\"https://www.ashutosh887.in/#person\",\"name\":\"Ashutosh Jha\",\"givenName\":\"Ashutosh\",\"familyName\":\"Jha\",\"jobTitle\":\"AI and Full Stack Engineer\",\"description\":\"AI and Full Stack Engineer at Insitu in Bengaluru. Builds agent budgets, voice workflows, vision adjudication, and streaming telemetry on ClickHouse and Aurora DSQL.\",\"worksFor\":{\"@type\":\"Organization\",\"name\":\"Insitu\"},\"url\":\"https://www.ashutosh887.in\",\"mainEntityOfPage\":\"https://www.ashutosh887.in\",\"sameAs\":[\"https://github.com/ashutosh887\",\"https://stackoverflow.com/users/14923299/ashutosh887\",\"https://leetcode.com/u/ashutosh887/\",\"https://codeforces.com/profile/ashutosh887\",\"https://www.linkedin.com/in/ashutosh887\",\"https://x.com/ashutosh887_\",\"https://instagram.com/ashutosh887_\",\"https://www.credly.com/users/ashutosh887\"],\"memberOf\":[{\"@type\":\"OrganizationRole\",\"roleName\":\"Organising Team\",\"startDate\":\"2025\",\"memberOf\":{\"@type\":\"Organization\",\"name\":\"AWS User Group Bengaluru\",\"url\":\"https://www.meetup.com/awsugblr/\"}},{\"@type\":\"OrganizationRole\",\"roleName\":\"Volunteer Team\",\"startDate\":\"2023\",\"memberOf\":{\"@type\":\"Organization\",\"name\":\"DevOpsDays Bengaluru\",\"url\":\"https://devopsdays.org/events/2023-bengaluru/welcome/\"}},{\"@type\":\"OrganizationRole\",\"roleName\":\"Chapter Lead, Bhopal and Karnataka\",\"startDate\":\"2022\",\"endDate\":\"2024\",\"memberOf\":{\"@type\":\"Organization\",\"name\":\"The Phoenix Guild\",\"url\":\"https://x.com/PhoenixGuildHQ/status/1663918942853668866\"}}],\"email\":\"[email protected]\",\"address\":{\"@type\":\"PostalAddress\",\"addressLocality\":\"Bengaluru\",\"addressRegion\":\"Karnataka\",\"addressCountry\":\"IN\"},\"alumniOf\":{\"@type\":\"EducationalOrganization\",\"name\":\"Lakshmi Narain College of Technology\",\"address\":{\"@type\":\"PostalAddress\",\"addressLocality\":\"Bhopal\",\"addressRegion\":\"Madhya Pradesh\",\"addressCountry\":\"IN\"}},\"knowsAbout\":[\"Software Engineering\",\"Artificial Intelligence\",\"LLM and Agent Systems\",\"AI Infrastructure\",\"Retrieval-Augmented Generation\",\"Vector Search\",\"Semantic Embeddings\",\"Prompt Engineering\",\"Model Context Protocol\",\"Reinforcement Learning\",\"Machine Learning\",\"Full Stack Development\",\"Distributed Backends\",\"Data Pipelines\",\"Observability\",\"Cloud Infrastructure\",\"Amazon Web Services\",\"Amazon EC2\",\"Amazon S3\",\"Amazon Aurora\",\"Aurora DSQL\",\"Google Cloud\",\"Google Cloud Run\",\"Docker\",\"Kubernetes\",\"Redis\",\"ClickHouse\",\"PostgreSQL\",\"React.js\",\"Next.js\",\"Node.js\",\"FastAPI\",\"TypeScript\",\"Python\",\"Go\",\"Solidity\",\"OpenAI API\",\"GPT-4\",\"Anthropic Claude\",\"Voice AI\",\"CIBA\",\"Web3 Development\",\"Smart Contracts\",\"Payment Workflows\",\"x402\",\"Cross-chain\",\"Bridging risk\",\"Solana\",\"Ethereum\",\"Hardhat\"],\"hasOccupation\":{\"@type\":\"Occupation\",\"name\":\"AI and Full Stack Engineer\",\"occupationLocation\":{\"@type\":\"City\",\"name\":\"Bengaluru\"},\"skills\":\"JavaScript, TypeScript, Python, Go, Java, SQL, Solidity, Rust, React.js, Next.js, React Native, Redux, TailwindCSS, HTML5, CSS3, Node.js, Express.js, NestJS, FastAPI, REST APIs, WebSockets, Microservices, OpenAI API, GPT-4, Anthropic Claude, Google Gemini API, LLMs, AI Agents, RAG, Vector Search, Semantic Embeddings, Evals, Prompt Engineering, LangChain, Model Context Protocol, Reinforcement Learning, Voice AI, CIBA, PostgreSQL, MongoDB, Redis, ClickHouse, Supabase, Firebase, Prisma ORM, Solana, Anchor Framework, Polkadot.js, Smart Contracts, Web3, DApps, Ethereum, x402, Cross-chain, Bridging risk, AWS, Amazon EC2, Amazon S3, Amazon Aurora, Aurora DSQL, Google Cloud, Google Cloud Run, Docker, Kubernetes, CI/CD, GitHub Actions, Linux, Observability, Datadog, Confluent, Git, Postman, Figma, Jest, System Design, Performance Optimization\"},\"hasCredential\":[{\"@type\":\"EducationalOccupationalCredential\",\"credentialCategory\":\"degree\",\"educationalLevel\":\"Bachelor's Degree\",\"name\":\"Bachelor of Technology in Computer Science Engineering\",\"about\":{\"@type\":\"EducationalOrganization\",\"name\":\"Lakshmi Narain College of Technology\"}},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/16fd70e2-0188-4dde-b896-bdcbbb9aaeb9#credential\",\"credentialCategory\":\"certification\",\"name\":\"Claude Certified Developer - Foundations\",\"url\":\"https://www.credly.com/badges/16fd70e2-0188-4dde-b896-bdcbbb9aaeb9\",\"
6identifier\":\"16fd70e2-0188-4dde-b896-bdcbbb9aaeb9\",\"dateCreated\":\"2026-09-27\",\"expires\":\"2027-09-27\",\"image\":\"https://www.ashutosh887.in/images/badges/claude-certified-developer-foundations.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"Anthropic\"},\"competencyRequired\":[\"Agent development\",\"Application Security\",\"Claude API integration\",\"Context engineering\",\"Eval \u0026 debugging\",\"MCP Server Development\",\"Model Optimization\",\"Prompt Engineering\"]},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/69048709-7ebe-4acf-ad2d-dfcd09754bff#credential\",\"credentialCategory\":\"certification\",\"name\":\"CyberOps Associate\",\"url\":\"https://www.credly.com/badges/69048709-7ebe-4acf-ad2d-dfcd09754bff\",\"identifier\":\"69048709-7ebe-4acf-ad2d-dfcd09754bff\",\"dateCreated\":\"2022-07-13\",\"image\":\"https://www.ashutosh887.in/images/badges/cyberops-associate.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"Cisco\"},\"competencyRequired\":[\"Attack Methods\",\"Computer Forensics\",\"Cryptography\",\"Cybersecurity\",\"Data And Event Analysis\",\"Endpoint Threat Analysis\",\"Host-based Analysis\",\"Incident Response\",\"Malware Analysis\",\"Network Attacks\",\"Network Intrusion Analysis SecOps\",\"SOC Metrics\",\"Security Concepts\",\"Security Monitoring\",\"Security Policy\",\"Security Procedures\",\"Threat Detection\"]},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/59c573d4-6dd6-4cea-b469-dc9bdc5ef335#credential\",\"credentialCategory\":\"certification\",\"name\":\"Introduction to Cybersecurity\",\"url\":\"https://www.credly.com/badges/59c573d4-6dd6-4cea-b469-dc9bdc5ef335\",\"identifier\":\"59c573d4-6dd6-4cea-b469-dc9bdc5ef335\",\"dateCreated\":\"2022-07-03\",\"image\":\"https://www.ashutosh887.in/images/badges/introduction-to-cybersecurity.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"Cisco\"},\"competencyRequired\":[\"Cyber Best Practices\",\"Cybersecurity\",\"Network Vulnerabilities\",\"Privacy And Data Confidentiality\",\"Threat Detection\"]},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/ffaee72b-bd73-4f49-8d31-9e9ae0613651#credential\",\"credentialCategory\":\"certification\",\"name\":\"Cybersecurity Fundamentals\",\"url\":\"https://www.credly.com/badges/ffaee72b-bd73-4f49-8d31-9e9ae0613651\",\"identifier\":\"ffaee72b-bd73-4f49-8d31-9e9ae0613651\",\"dateCreated\":\"2022-03-28\",\"image\":\"https://www.ashutosh887.in/images/badges/cybersecurity-fundamentals.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"IBM SkillsBuild\"},\"competencyRequired\":[\"Cryptography\",\"Cyber Attacks\",\"Cyber Threat Analysis\",\"Cyber Threat Intelligence\",\"Cybersecurity\",\"Cybersecurity Processes\",\"Cybersecurity Risk Management\",\"Incident Response\",\"Information Security\",\"Security Strategies\",\"Social Engineering\",\"Threat Analysis\",\"Threat Detection\",\"Vulnerability Management\"]},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/4fe1d202-03a1-42ca-a8e8-7af7e00681d1#credential\",\"credentialCategory\":\"certification\",\"name\":\"CCNA: Introduction to Networks\",\"url\":\"https://www.credly.com/badges/4fe1d202-03a1-42ca-a8e8-7af7e00681d1\",\"identifier\":\"4fe1d202-03a1-42ca-a8e8-7af7e00681d1\",\"dateCreated\":\"2022-01-14\",\"image\":\"https://www.ashutosh887.in/images/badges/ccna-introduction-to-networks.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"Cisco\"},\"competencyRequired\":[\"Ethernet\",\"IP Subnetting\",\"IP connectivity\",\"IP services\",\"IPv4 And IPv6 Addressing\",\"Network Fundamentals\",\"Security Fundamentals\",\"Switching\"]},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/e8ef4a61-8e5f-4250-bf4c-e8afc66f9bb3#credential\",\"credentialCategory\":\"certification\",\"name\":\"Introduction to Packet Tracer\",\"url\":\"https://www.credly.com/badges/e8ef4a61-8e5f-4250-bf4c-e8afc66f9bb3\",\"identifier\":\"e8ef4a61-8e5f-4250-bf4c-e8afc66f9bb3\",\"dateCreated\":\"2022-01-13\",\"image\":\"https://www.ashutosh887.in/images/badges/introduction-to-packet-tracer.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"Cisco\"},\"competencyRequired\":[\"Cisco Packet Tracer\",\"IoT Simulation\",\"Network Simulation\"]},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/84e485f2-a0f7-4582-ba27-07c38a0f8e4f#credential\",\"credentialCategory\":\"certification\",\"name\":\"AWS Academy Graduate - Cloud Foundations - Training Badge\",\"url\":\"https://www.credly.com/badges/84e485f2-a0f7-4582-ba27-07c38a0f8e4f\",\"identifier\":\"84e485f2-a0f7-4582-ba27-07c38a0f8e4f\",\"dateCreated\":\"2021-12-25\",\"image\":\"https://www.ashutosh887.in/images/badges/aws-academy-graduate-cloud-foundations.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"Amazon Web Services\"},\"competencyRequired\":[\"AWS Architecture\",\"AWS Cloud\",\"AWS Core Services\",\"AWS Pricing\",\"AWS Support\"]},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/f2586622-bbc5-4af4-93e3-50b31f9a41b6#credential\",\"credentialCategory\":\"certification\",\"name\":\"AWS Academy Graduate - Machine Learning Foundations - Training Badge\",\"url\":\"https://www.credly.com/badges/f2586622-bbc5-4af4-93e3-50b31f9a41b6\",\"identifier\":\"f2586622-bbc5-4af4-93e3-50b31f9a41b6\",\"dateCreated\":\"2021-12-25\",\"image\":\"https://www.ashutosh887.in/images/badges/aws-academy-graduate-machine-learning-foundations.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"Amazon Web Services\"},\"competencyRequired\":[\"AWS\",\"AWS Cloud Computing\",\"Artificial Intelligence: Machine Learning\",\"Machine Learning\",\"Machine Learning (ML) Foundations\"]},{\"@type\":\"EducationalOccupationalCredential\",\"@id\":\"https://www.credly.com/badges/87e3a099-36c5-456f-94ea-84068db07d4c#credential\",\"credentialCategory\":\"certification\",\"name\":\"Enterprise Design Thinking Practitioner\",\"url\":\"https://www.credly.com/badges/87e3a099-36c5-456f-94ea-84068db07d4c\",\"identifier\":\"87e3a099-36c5-456f-94ea-84068db07d4c\",\"dateCreated\":\"2021-06-26\",\"image\":\"https://www.ashutosh887.in/images/badges/enterprise-design-thinking-practitioner.png\",\"recognizedBy\":{\"@type\":\"Organization\",\"name\":\"IBM\"},\"competencyRequired\":[\"Design\",\"Empathy\",\"Experience Design\",\"Ideation\",\"UX\",\"User Experience\",\"User Research\",\"User-Centered Design\",\"User-Centric\"]}],\"image\":{\"@type\":\"ImageObject\",\"url\":\"https://www.ashutosh887.in/opengraph-image\",\"width\":1200,\"height\"
6:630},\"nationality\":{\"@type\":\"Country\",\"name\":\"India\"}},{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"@id\":\"https://www.ashutosh887.in/#website\",\"url\":\"https://www.ashutosh887.in\",\"name\":\"Ashutosh Jha Portfolio\",\"description\":\"Portfolio of Ashutosh Jha, an AI and full stack engineer. Agent systems, backends, and the cloud infrastructure under them.\",\"publisher\":{\"@id\":\"https://www.ashutosh887.in/#person\"},\"inLanguage\":\"en-IN\",\"copyrightYear\":2026,\"creator\":{\"@id\":\"https://www.ashutosh887.in/#person\"}},{\"@context\":\"https://schema.org\",\"@type\":\"ProfessionalService\",\"@id\":\"https://www.ashutosh887.in/#service\",\"name\":\"Ashutosh Jha - Software Engineering Services\",\"description\":\"AI and full stack engineering: agent systems, RAG pipelines, product work, and the backends and cloud infrastructure under them. Available for full-time roles and consulting.\",\"provider\":{\"@id\":\"https://www.ashutosh887.in/#person\"},\"address\":{\"@type\":\"PostalAddress\",\"addressLocality\":\"Bengaluru\",\"addressRegion\":\"Karnataka\",\"addressCountry\":\"IN\"},\"areaServed\":{\"@type\":\"GeoCircle\",\"geoMidpoint\":{\"@type\":\"GeoCoordinates\",\"latitude\":\"12.9716\",\"longitude\":\"77.5946\"},\"geoRadius\":\"50000\"},\"hasOfferCatalog\":{\"@type\":\"OfferCatalog\",\"name\":\"Development Services\",\"itemListElement\":[{\"@type\":\"Offer\",\"itemOffered\":{\"@type\":\"Service\",\"name\":\"AI Engineering\",\"description\":\"LLM and agent systems, RAG pipelines, evals, and MCP integrations in Python and TypeScript\"}},{\"@type\":\"Offer\",\"itemOffered\":{\"@type\":\"Service\",\"name\":\"Full Stack Development\",\"description\":\"Web applications end to end with Next.js, React, Node.js, FastAPI, and PostgreSQL\"}},{\"@type\":\"Offer\",\"itemOffered\":{\"@type\":\"Service\",\"name\":\"Cloud and Infrastructure\",\"description\":\"Backends, data pipelines, and observability on AWS and Google Cloud, with Docker and Kubernetes\"}},{\"@type\":\"Offer\",\"itemOffered\":{\"@type\":\"Service\",\"name\":\"Web3 Development\",\"description\":\"Smart contracts, Solana programs, and wallet integrations\"}}]}},{\"@context\":\"https://schema.org\",\"@type\":\"ItemList\",\"@id\":\"https://www.ashutosh887.in/#projects\",\"name\":\"Projects by Ashutosh Jha\",\"description\":\"Agent infrastru
6cture, sales and learning environments, prompt evolution and audio QC — including Stub (budget gate for agents, on npm), NeverLose (real-time buyer agent), FinQuery (OpenEnv for finance), Evolv (prompt DNA), WinterArc (offline-first habit tracker), and StudioCast (audio drama QC).\",\"numberOfItems\":32,\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"Stub\",\"description\":\"A drop-in budget gate for AI agents that spend real money. Covers paid APIs, x402 micropayments, and LLM tokens. One enforceable budget in front of the whole fleet, with an exact double-entry record of every agent's spend. Uses a reserve → pay → settle flow so irreversible payments fire exactly once, even under retries or crashes.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/stub\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":2,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"Signet\",\"description\":\"An identity and governance layer for AI agents. Every action is wrapped in a signed, verifiable envelope and policy gated before execution. Ships with Python and TypeScript SDKs plus MCP/A2A middleware for drop-in adoption across agent stacks.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/signet\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":3,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"NeverLose\",\"description\":\"An AI sales agent that works on hesitant buyers in real time. It reads 11 buyer signals and runs an escalating negotiation before the customer leaves. Two-sided: a customer-facing sales agent plus a merchant intelligence copilot on shared infrastructure. Finalist (Top 5 of 90+) at the Pine Labs AI Hackathon.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/neverlose\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":4,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"FinQuery\",\"description\":\"An OpenEnv-compatible reinforcement learning environment for financial reasoning. Each reset procedurally generates a verifiable finance question. The agent decides which data to fetch and how to combine it, earning dense per-step rewards. Covers 25 companies across 7 sectors over 9 years (2017-2025).\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/finquery\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":5,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"Evolv\",\"description\":\"Prompt evolution as genetic sequences. Evolv extracts a DNA fingerprint from every prompt, clusters them semantically with embeddings, synthesizes templates from the clusters, and tracks each mutation and its lineage. Won 1st prize at the Portkey AI Builder Challenge.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/evolv\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":6,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"WinterArc\",\"description\":\"An offline-first habit tracker for a fixed run of days. October 1 through December 31 is the winter arc, but you can set any dates. All habit data stays in your browser. No account, no sync, no backend. Ships as a PWA you can add to your home screen, with a warm-up window, rest days, a grid for the full run, per-habit rings and streaks, local reminders, and JSON and CSV export.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/winterarc\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":7,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"saathi\",\"description\":\"If you can say it, it gets done. Saathi is a voice-first workflow engine where a JSON file runs as a spoken conversation in Kannada, Hindi or English. Talk a form into existence one question at a time, or bridge a call between two people who do not share a language. A resolver cascade handles closed sets and rules for free before calling a model, and the engine refuses to guess below 0.75 confidence.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/saathi\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}
6},{\"@type\":\"ListItem\",\"position\":8,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"Request Layer\",\"description\":\"Three-tier cache, coalescer, and dollar-aware rate limits for the agent fleet. Request Layer sits between Kong and the Nasiko agent fleet. It adds L1 exact, L2 semantic, and L3 router-decision caching, collapses 200 concurrent duplicates into one origin call with an in-flight coalescer, and gates traffic with a per-agent token-bucket, rolling dollar-per-minute meter, and three-lane priority queue. Observable via admin REST and SSE with Phoenix cache.hit spans.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/request-layer\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":9,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"ClickLiv\",\"description\":\"Real-time foreground-only concurrency for SonyLIV streaming telemetry, on ClickHouse. ClickLiv ingests 7 million session events into ClickHouse, reconstructs truly active playback intervals, and rolls them to one row per session minute. It serves peak and average concurrency at any grain and filter combination from that rollup, with incremental handling of still-open sessions. Same numbers power the web dashboard, conversational surface, and MCP server through one budgeted read-only role.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/clickliv\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":10,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"StudioCast\",\"description\":\"The quality layer for AI audio drama. Paste a chapter and StudioCast directs it into a multi-voice scene, then listens to its own render. It re-transcribes the audio, checks emotion two independent ways, measures pacing and loudness, and holds lines that miss their direction.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/studiocast\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":11,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"verdex\",\"description\":\"Image-grounded adjudication for damage claims. Verdex looks at the photos for a claim and decides what the pixels show. It treats the chat and text inside images as untrusted data and returns supported, contradicted, or not enough information. Images decide. History only adds a risk flag.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/verdex\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":12,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"Plumb\",\"description\":\"Signer-side security for Solana multisigs. Plumb is a browser extension that sits on the Squads V4 approval modal and shows what you are about to sign in plain English. It decodes durable-nonce replay windows, flags owner-mismatched nonce accounts, diffs account and authority changes via Surfpool simulation, and diffs BPF bytecode for program upgrades. Read-only at the signer interface, it never signs or modifies the transaction.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/plumb\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":13,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"Darwin\",\"description\":\"Self-evolving AI agents via git-native natural selection. Darwin keeps agent config in git and uses the history as the evolution engine. A subject agent tries a task, a reviewer scores it, and an orchestrator branches, mutates SOUL.md and RULES.md, validates, and merges only the fitter version. Every generation is a commit, every trait is traceable with blame and diff.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/darwin\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":14,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"ClawGuard\",\"description\":\"Local AI that safely touches the world, with zero token exposure. Core reasoning runs locally. A cloud intermediary exchanges scoped tokens through Auth0 Token Vault, so OAuth tokens never reach the device. Every external 
6call is gated by permission preview, offline queue, anomaly shield, and CIBA step-up, with a live SSE audit trail and one-click revoke in under two seconds.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/clawguard\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":15,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"Stoq\",\"description\":\"The AI that makes 13.7 million kiranas think, stock, buy, lend, and compete as one. Stoq is a coordination layer on Paytm Soundbox that turns isolated kiranas into a mesh. It infers stock from supplier payments, pools demand for 14 to 20 percent bulk savings, forecasts cash flow and routes mesh credit at 6 to 8 percent APR, and handles GST compliance. Voice-first in 11 languages, with Soundbox and WhatsApp briefings.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/stoq\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":16,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"FaultLine\",\"description\":\"Root-cause analysis for AI decisions. FaultLine instruments an agent with an SDK, captures every step to an ingest API, and a BullMQ worker turns the trace into an incident report. It builds a timeline, names the root cause and contributing factors, and lists fixes with evidence from the trace.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/faultline\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":17,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"FeelTheWeb\",\"description\":\"An AI-powered plugin that turns what is on screen into haptic patterns. FeelTheWeb is a plugin for Logitech MX hardware. Claude Haiku 4.5 maps the page every 1 to 2 seconds, then the mouse plays distinct patterns for links, buttons, text, images, and empty space, the Creative Console shows a 3 by 3 spatial map, and voice AI narrates on demand.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/feeltheweb\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":18,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"moodcast\",\"description\":\"Turn any text into emotionally expressive audio with ambient soundscapes. Moodcast is a Moltbot/OpenClaw skill on ElevenLabs v3. It detects emotion in text and inserts audio tags to shape delivery, then renders speech with a matching ambient soundscape from the Sound Effects API. Mood presets map to voices, long text is split automatically, and the CLI can save to file or show the enhanced text before generation.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/moodcast\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":19,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"BridgeRadar\",\"description\":\"See what could go wrong before you bridge. BridgeRadar simulates a bridge transaction before you sign it. It pulls every LI.FI route for the pair, scores each one for security, liquidity and failure rate, and shows expected versus worst case outcomes so you pick with eyes open.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/bridgeradar\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":20,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"PayFlow\",\"description\":\"Visual programmable payment workflows with MNEE. PayFlow lets you build payment logic on a canvas and ship it on Ethereum Sepolia with the MNEE token. Create milestone releases, revenue splits, and multi-party approvals that pause, resume, and deploy on the spot. A FlowFactory deploys each flow as its own contract.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/payflow\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":21,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"AlivePing\",\"description\":\"Your last-mile personal safety system, built on Solana. AlivePing watches a check-in window and fires if you miss it, with a panic button for immediate help. Every session is written to Solana testnet as tamper-proof proof, alerts go out over WhatsApp via the Meta Business API, and location and events stream in real time through Confluent.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/aliveping\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}
6},{\"@type\":\"ListItem\",\"position\":22,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"SafeVoice\",\"description\":\"AI-powered legal evidence documentation for victims of abuse. SafeVoice opens as a decoy meditation app and reveals its real flow only after long-press and PIN. A victim speaks, the app transcribes, asks gentle follow-ups, and builds a secure evidence timeline with escalation detection. Calming guidance is voiced with ElevenLabs, reasoning runs on Gemini, and exits are instant for high-risk environments.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/safevoice\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":23,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"ShotLock\",\"description\":\"Deterministic creative control for AI-generated visuals. ShotLock is a visual generation tool on Bria FIBO where you lock camera and composition and then iterate on lighting, color, and mood. A proof grid shows variations side by side so teams keep outputs consistent across a creative workflow. Built on Next.js, Prisma, and MongoDB.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/shotlock\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}}
6,{\"@type\":\"ListItem\",\"position\":24,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"CareerFit\",\"description\":\"We do not prepare you. We qualify you. CareerFit reads a resume from PDF, DOCX, or image, extracts skills and level, and scores hire probability against live market demand. It shows gaps, salary ranges, and trends, then returns a roadmap of projects with impact estimates, plus role-specific mock interviews with feedback and tracked history.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/careerfit\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":25,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"LaunchKit\",\"description\":\"Ship fast. Get customers faster. LaunchKit reads any website, infers the ideal customer profile, and turns it into a GTM plan. It writes the messaging framework and the execution checklist so founders move from analysis to outreach without starting from a blank page.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/launchkit\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":26,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"CivicLens\",\"description\":\"Bringing clarity to public services for everyone. CivicLens is a chat interface for government schemes and civic processes. Ask in plain English, get streaming answers on eligibility and how to apply, with entity extraction and query classification underneath. Upload a PDF to ground the answer, crawl portals and parse PDFs via Kestra workflows, and optionally fine-tune with a small Oumi dataset.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/civiclens\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":27,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"DevBuzz\",\"description\":\"Where developers build, share, and grow. DevBuzz is a community platform with OTP login, session cookies, and a feed with infinite scroll. Posts support threaded nested comments with single upvote per user, inline replies, and toast feedback. Built on Next.js App Router, Prisma and Neon Postgres, with Redux Toolkit for state and Resend for email.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/devbuzz\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":28,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"PolkaSafe\",\"description\":\"Multisig and treasury infrastructure for Polkadot. PolkaSafe ran the primary multisig for Polkadot, Kusama, Astar, Aleph Zero and EVM chains, with peak $300M under management. Built on Substrate's multisig and proxy pallets, it handled N-of-M signing, batch extrinsics, on-chain treasury votes, and hardware signing via Polkadot Vault. I worked on the UI with Polkadot.js and Firebase Auth. Archived May 2026.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/polkasafe\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":29,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"Trance\",\"description\":\"An online music streaming web application. Trance is a streaming app focused on shuffling and playlist curation. Browse artists, build playlists, and play through a custom player built on Next.js and Prisma. Version 1 is deprecated while version 2 is in development.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/trance\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":30,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"ShoppersEnd\",\"description\":\"Gamified e-commerce. ShoppersEnd is a full stack store where discounts are earned through achievements and loyalty points. It handles cart, checkout, order tracking, and personalized recommendations, with a React and Material UI frontend and a Node, Express, and MongoDB backend with Stripe.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/shoppersend\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}
6},{\"@type\":\"ListItem\",\"position\":31,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"depextract\",\"description\":\"A convenient CLI tool for dependency extraction. Point depextract at a package.json and it lists production and dev dependencies, then generates an install script for npm, yarn, or pnpm. Run with npx depextract with no install, pick the location of the package.json, and the script lands in scripts.sh.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/depextract\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}},{\"@type\":\"ListItem\",\"position\":32,\"item\":{\"@type\":\"SoftwareApplication\",\"name\":\"ethsapien\",\"description\":\"Decentralized AI-powered credentialing for on-chain identity and reputation. Ethsapien issues verifiable credentials on chain for identity and reputation. Cairo and Solidity contracts manage issuance and verification, with a Next.js app for handling credentials. Built as an early experiment in AI-assisted credentialing.\",\"operatingSystem\":\"Web\",\"url\":\"https://www.ashutosh887.in/projects/ethsapien\",\"author\":{\"@id\":\"https://www.ashutosh887.in/#person\"}}}]}]}7:X\n0:{\"P\":null,\"c\":[\"\",\"writing\",\"evals-are-the-product\"],\"q\":\"\",\"i\":false,\"f\":[[[\"\",{\"children\":[\"writing\",{\"children\":[[\"slug\",\"evals-are-the-product\",\"d\",[]],{\"children\":[\"__PAGE__\",{},\"$undefined\",\"$undefined\",4608]},\"$undefined\",\"$undefined\",4608]},\"$undefined\",\"$undefined\",4608]},\"$undefined\",\"$undefined\",4624],[[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/immutable/chunks/2l4hswa-ubkpn.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/immutable/chunks/19s7px060v539.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-4\",{\"src\":\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-5\",{\"src\":\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en-IN\",\"suppressHydrationWarning\":true,\"className\":\"bricolage_grotesque_6c0e643-module___gO8iW__variable geist_d633ac5f-module__BboVrW__variable geist_mono_768fb615-module__nw7kYW__variable\",\"children\":[[\"$\",\"head\",null,{\"children\":[[\"$\",\"script\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"(function(){try{var t=localStorage.getItem(\\\"portfolio-theme\\\");if(!t||[\\\"cyan\\\",\\\"violet\\\",\\\"emerald\\\",\\\"amber\\\",\\\"rose\\\"].indexOf(t)\u003c0){t=\\\"cyan\\\"}document.documentElement.dataset.theme=t}catch(e){document.documentElement.dataset.theme=\\\"cyan\\\"}})()\"}}],[\"$\",\"link\",null,{\"rel\":\"preconnect\",\"href\":\"https://www.googletagmanager.com\",\"crossOrigin\":\"anonymous\"}],[\"$\",\"link\",null,{\"rel\":\"preconnect\",\"href\":\"https://www.clarity.ms\",\"crossOrigin\":\"anonymous\"}],[\"$\",\"link\",null,{\"rel\":\"dns-prefetch\",\"href\":\"https://www.googletagmanager.com\"}],[\"$\",\"link\",null,{\"rel\":\"dns-prefetch\",\"href\":\"https://www.clarity.ms\"}],[\"$\",\"meta\",null,{\"name\":\"geo.region\",\"content\":\"IN-KA\"}],[\"$\",\"meta\",null,{\"name\":\"geo.placename\",\"content\":\"Bengaluru\"}],[\"$\",\"meta\",null,{\"name\":\"geo.position\",\"content\":\"12.9716;77.5946\"}],[\"$\",\"meta\",null,{\"name\":\"ICBM\",\"content\":\"12.9716, 77.5946\"}],[\"$\",\"script\",null,{\"type\":\"application/ld+json\",\"dangerouslySetInnerHTML\":{\"__html\":\"$2\"}}]]}],\"$L3\"]}]]}],{\"children\":[\"$L4\",{\"children\":[\"$L5\",{\"children\":[\"$L6\",{}
6,null,false,null]},null,false,\"$7\"]},null,false,\"$7\"]},null,false,null],\"$L8\",false]],\"m\":\"$undefined\",\"G\":[\"$9\",[\"$La\"]],\"S\":true,\"h\":null,\"r\":\"$undefined\",\"s\":\"$undefined\",\"a\":\"$undefined\",\"l\":\"$undefined\",\"p\":\"$undefined\",\"d\":\"$undefined\",\"b\":\"qoNV2rKveVTRyG0blBhmA\"}\nb:I[79520,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\"],\"\"]\nc:I[69268,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\"],\"default\"]\nd:I[66326,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\"],\"default\"]\ne:I[34107,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\"],\"default\"]\nf:I[47420,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\"],\"default\"]\n10:I[8583,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\"],\"ClarityProvider\"]\n11:I[39756,[\"/_next/static/immutable/chunks/1tf2pn9278k7y.js\"],\"default\"]\n12:I[37457,[\"/_next/static/immutable/chunks/1tf2pn9278k7y.js\"],\"default\"]\n13:I[80135,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\",\"/_next/static/immutable/chunks/0xbp3crmj8tk4.js\"],\"default\"]\n14:I[81749,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\",\"/_next/static/immutable/chunks/2pa3wur8avg6r.js\"],\"default\"]\n15:I[88902,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\",\"/_next/static/immutable/chunks/2pa3wur8avg6r.js\"],\"default\"]\n16:I[22016,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\",\"/_next/static/immutable/chunks/0xbp3crmj8tk4.js\"],\"\"]\n17:I[5014,[\"/_next/static/immutable/chunks/19s7px060v539.js\",\"/_next/static/immutable/chunks/1a_43ptwezuwl.js\",\"/_next/static/immutable/chunks/09dv42b2n4kp8.js\",\"/_next/static/immutable/chunks/2ffteh9vf_1wl.js\",\"/_next/static/immutable/chunks/0q4r2h8-bzpex.js\",\"/_next/static/immutable/chunks/0gr14mxkka9yj.js\",\"/_next/static/immutable/chunks/0xbp3crmj8tk4.js\"],\"default\"]\n1b:I[97367,[\"/_next/static/immutable/chunks/1tf2pn9278k7y.js\"],\"OutletBoundary\"]\n1c:\"$Sreact.suspense\"\n1e:I[97367,[\"/_next/static/immutable/chunks/1tf2pn9278k7y.js\"],\"ViewportBoundary\"]\n20:I[97367,[\"/_next/static/immutable/chunks/1tf2pn9278k7y.js\"],\"MetadataBoundary\"]\n3:[\"$\",\"body\",null,{\"className\":\"bg-canvas text-ink font-sans antialiased\",\"children\":[[[\"$\",\"$Lb\",null,{\"strategy\":\"lazyOnload\",\"src\":\"https://www.googletagmanager.com/gtag/js?i
6d=G-NL02FGDHFN\"}],[\"$\",\"$Lb\",null,{\"id\":\"google-analytics-script\",\"strategy\":\"lazyOnload\",\"children\":\"\\n                window.dataLayer = window.dataLayer || [];\\n                function gtag(){dataLayer.push(arguments);}\\n                gtag('js', new Date());\\n                gtag('config', 'G-NL02FGDHFN', {\\n                  page_path: window.location.pathname,\\n                });\\n              \"}]],[\"$\",\"a\",null,{\"href\":\"#main-content\",\"className\":\"sr-only focus:not-sr-only focus:fixed focus:left-4 focus:top-4 focus:z-200 focus:inline-flex focus:items-center focus:rounded-full focus:bg-accent focus:px-5 focus:py-2.5 focus:text-sm focus:font-semibold focus:text-accent-contrast focus:shadow-xl focus:shadow-black/40 focus:outline-none focus:ring-2 focus:ring-white/60\",\"children\":\"Skip to content\"}],[\"$\",\"$Lc\",null,{}],[\"$\",\"$Ld\",null,{\"askAiEnabled\":false}],[\"$\",\"$Le\",null,{\"askAiEnabled\":false}],[\"$\",\"$Lf\",null,{\"children\":[\"$\",\"$L10\",null,{\"projectId\":\"urir5c0lat\",\"children\":[\"$\",\"$L11\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[[\"$\",\"div\",null,{\"aria-hidden\":true,\"className\":\"template-curtain pointer-events-none fixed inset-0 z-70 bg-canvas\"}],[\"$\",\"div\",null,{\"className\":\"template-content\",\"children\":[\"$\",\"$L12\",null,{}]}]],\"templateStyles\":[],\"templateScripts\":null,\"notFound\":[[[\"$\",\"div\",null,{\"aria-hidden\":true,\"className\":\"pointer-events-none fixed inset-0 z-0\",\"children\":[[\"$\",\"$L13\",null,{\"density\":0.9}],[\"$\",\"div\",null,{\"className\":\"absolute inset-0\",\"style\":{\"background\":\"radial-gradient(60% 50% at 75% 10%, rgb(var(--accent) / 0.05), transparent 70%)\"}}],[\"$\",\"div\",null,{\"className\":\"absolute inset-0\",\"style\":{\"background\":\"radial-gradient(45% 40% at 12% 88%, rgb(var(--accent) / 0.06), transparent 70%)\"}}]]}],[\"$\",\"div\",null,{\"className\":\"relative z-10 flex min-h-svh flex-col\",\"children\":[[\"$\",\"main\",null,{\"id\":\"main-content\",\"className\":\"flex-1\",\"children\":[\"$\",\"div\",null,{\"className\":\"shell page-pad\",\"children\":[\"$\",\"div\",null,{\"className\":\"flex min-h-[60vh] flex-col justify-center\",\"children\":[[\"$\",\"header\",null,{\"className\":\"sm:flex sm:items-center sm:justify-between sm:gap-8\",\"children\":[[\"$\",\"div\",null,{\"className\":\"min-w-0\",\"children\":[[\"$\",\"p\",null,{\"className\":\"section-eyebrow\",\"children\":[\"$\",\"$L14\",null,{\"text\":\"404\"}]}],[\"$\",\"h1\",null,{\"className\":\"text-balance font-display text-4xl font-bold normal-case leading-[1.05] tracking-[-0.03em] text-ink sm:text-5xl sm:leading-[0.95] mt-3 sm:mt-4\",\"aria-label\":\"Page not found\",\"children\":[\"$\",\"$L15\",null,{\"text\":\"Page not found\"}]}],[\"$\",\"p\",null,{\"className\":\"mt-4 max-w-2xl text-base leading-relaxed text-muted sm:mt-6 sm:text-lg\",\"children\":\"The page you're looking for doesn't exist or has moved.\"}]]}],null]}],[\"$\",\"div\",null,{\"className\":\"mt-8 sm:mt-10\",\"children\":[\"$\",\"$L16\",null,{\"href\":\"/\",\"className\":\"ghost-button\",\"children\":[[\"$\",\"$L17\",null,{\"ref\":\"$undefined\",\"iconNode\":[[\"path\",{\"d\":\"m12 19-7-7 7-7\",\"key\":\"1l729n\"}],[\"path\",{\"d\":\"M19 12H5\",\"key\":\"x3x0zl\"}]],\"className\":\"lucide-arrow-left h-4 w-4\",\"strokeWidth\":1.5}],\"Back home\"]}]}]]}]}]}],[\"$\",\"footer\",null,{\"className\":\"border-t border-hairline\",\"children\":[\"$\",\"div\",null,{\"className\":\"shell mx-auto flex w-full max-w-6xl flex-col items-center justify-between gap-3 py-6 pb-24 sm:flex-row lg:pb-6\",\"children\":[[\"$\",\"div\",null,{\"className\":\"flex flex-col gap-1\",\"children\":[\"$\",\"p\",null,{\"className\":\"mono-xs uppercase tracking-[0.14em] text-faint\",\"children\":[\"© \",[\"$\",\"span\",null,{\"children\":2026}],\" \",\"Ashutosh Jha\"]}]}],[\"$\",\"div\",null,{\"className\":\"flex flex-col items-center gap-3 sm:flex-row\",\"children\":[[\"$\",\"div\",null,{\"className\":\"flex items-center gap-3\",\"children\":[[\"$\",\"$L16\",null,{\"href\":\"/community\",\"className\":\"text-sm text-muted transition-colors duration-150 hover:text-ink\",\"children\":\"Community\"}],[\"$\",\"span\",null,{\"aria-hidden\":true,\"className\":\"h-4 w-px bg-hairline-strong\"}],[\"$\",\"$L16\",null,{\"href\":\"/contact\",\"className\":\"text-sm text-muted transition-colors duration-150 hover:text-ink\",\"children\":\"Get in touch\"}]]}],\"$L18\",\"$L19\"]}]]}]}]]}]],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]}]}]]}]\n4:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L11\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L12\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n5:[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L11\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L12\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}]\n6:[\"$\",\"$1\",\"c\",{\"children\":[\"$L1a\",[[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/immutable/chunks/0xbp3crmj8tk4.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"$L1b\",null,{\"children\":[\"$\",\"$1c\",null,{\"name\":\"Next.MetadataOutlet\",\"children\":\"$@1d\"}]}]]}]\n8:[\"$\",\"$1\",\"h\",{\"children\":[null,[\"$\",\"$L1e\",null,{\"children\":\"$L1f\"}],[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$L20\",null,{\"children\":[\"$\",\"$1c\",null,{\"name\":\"Next.Metadata\",\"children\":\"$L21\"}]}]}],[\"$\",\"meta\",null,{\"name\":\"next-size-adjust\",\"content\":\"\"}]]}]\na:[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/immutable/chunks/2l4hswa-ubkpn.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]\n7:C\n18:[\"$\",\"span\",null,{\"aria-hidden\":true,\"className\":\"hidden h-4 w-px bg-hairline-strong sm:block\"}]\n22:T518,M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z19:[\"$\",\"div\",null,{\"className\":\"flex items-center gap-3\",\"children\":[[[\"$\",\"a\",\"github\",{\"href\":\"https://github.com/ashutosh887\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"GitHub profile\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 496 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"$22\",\"children\":[]}
6]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}],[\"$\",\"a\",\"linkedin\",{\"href\":\"https://www.linkedin.com/in/ashutosh887\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"LinkedIn profile\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 448 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"M416 32H31.9C14.3 32 0 46.5 0 64.3v383.4C0 465.5 14.3 480 31.9 480H416c17.6 0 32-14.5 32-32.3V64.3c0-17.8-14.4-32.3-32-32.3zM135.4 416H69V202.2h66.5V416zm-33.2-243c-21.3 0-38.5-17.3-38.5-38.5S80.9 96 102.2 96c21.2 0 38.5 17.3 38.5 38.5 0 21.3-17.2 38.5-38.5 38.5zm282.1 243h-66.4V312c0-24.8-.5-56.7-34.5-56.7-34.6 0-39.9 27-39.9 54.9V416h-66.4V202.2h63.7v29.2h.9c8.9-16.8 30.6-34.5 62.9-34.5 67.2 0 79.7 44.3 79.7 101.9V416z\",\"children\":[]}]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}],[\"$\",\"a\",\"twitter\",{\"href\":\"https://x.com/ashutosh887_\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"X (Twitter) profile\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 512 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z\",\"children\":[]}]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}],\"$L23\",\"$L24\"],\"$L25\"]}]\n23:[\"$\",\"a\",\"instagram\",{\"href\":\"https://instagram.com/ashutosh887_\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"Instagram profile\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 448 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"M224.1 141c-63.6 0-114.9 51.3-114.9 114.9s51.3 114.9 114.9 114.9S339 319.5 339 255.9 287.7 141 224.1 141zm0 189.6c-41.1 0-74.7-33.5-74.7-74.7s33.5-74.7 74.7-74.7 74.7 33.5 74.7 74.7-33.6 74.7-74.7 74.7zm146.4-194.3c0 14.9-12 26.8-26.8 26.8-14.9 0-26.8-12-26.8-26.8s12-26.8 26.8-26.8 26.8 12 26.8 26.8zm76.1 27.2c-1.7-35.9-9.9-67.7-36.2-93.9-26.2-26.2-58-34.4-93.9-36.2-37-2.1-147.9-2.1-184.9 0-35.8 1.7-67.6 9.9-93.9 36.1s-34.4 58-36.2 93.9c-2.1 37-2.1 147.9 0 184.9 1.7 35.9 9.9 67.7 36.2 93.9s58 34.4 93.9 36.2c37 2.1 147.9 2.1 184.9 0 35.9-1.7 67.7-9.9 93.9-36.2 26.2-26.2 34.4-58 36.2-93.9 2.1-37 2.1-147.8 0-184.8zM398.8 388c-7.8 19.6-22.9 34.7-42.6 42.6-29.5 11.7-99.5 9-132.1 9s-102.7 2.6-132.1-9c-19.6-7.8-34.7-22.9-42.6-42.6-11.7-29.5-9-99.5-9-132.1s-2.6-102.7 9-132.1c7.8-19.6 22.9-34.7 42.6-42.6 29.5-11.7 99.5-9 132.1-9s102.7-2.6 132.1 9c19.6 7.8 34.7 22.9 42.6 42.6 11.7 29.5 9 99.5 9 132.1s2.7 102.7-9 132.1z\",\"children\":[]}
6]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}]\n24:[\"$\",\"a\",\"email\",{\"href\":\"mailto:[email protected]?subject=Hello%20from%20Portfolio\u0026body=Hi%20Ashutosh,%20I%20found%20your%20portfolio%20and%20would%20like%20to%20connect.\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"Email Ashutosh\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 512 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z\",\"children\":[]}]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}]\n25:[\"$\",\"a\",null,{\"href\":\"/feed.xml\",\"className\":\"relative text-faint transition-colors duration-150 hover:text-ink before:absolute before:-inset-3 before:rounded-full before:content-['']\",\"aria-label\":\"RSS feed\",\"children\":[\"$\",\"svg\",null,{\"width\":\"14\",\"height\":\"14\",\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":\"2\",\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",null,{\"d\":\"M4 11a9 9 0 0 1 9 9\"}],[\"$\",\"path\",null,{\"d\":\"M4 4a16 16 0 0 1 16 16\"}],[\"$\",\"circle\",null,{\"cx\":\"5\",\"cy\":\"19\",\"r\":\"1\"}]]}]}]\n26:T759,\u003cp\u003eEvery LLM project hits the point where the prompt stops being the artifact you care about and the eval suite takes its place. Rewriting a prompt takes five minutes. Knowing whether the rewrite was better takes far longer, and staring harder at the outputs does not close that gap. The evals are the only thing standing between \u0026#39;feels better on the three examples I tried\u0026#39; and \u0026#39;is better across the cases that matter.\u0026#39;\u003c/p\u003e\n\u003cp\u003eMost teams write their evals once, watch them go green, and never look again. Unit tests survive that treatment. Evals do not, because LLM behavior drifts with every model bump, prompt tweak, and retrieval change, and a stale eval set stops measuring the thing you actually ship. I have had better luck treating the set as a living spec. Every bug report becomes a case. Every regression becomes a case. The suite grows toward the real distribution of how the system gets used, which is the only distribution worth scoring against.\u003c/p\u003e\n\u003cp\u003eGraders are where this gets hard. Exact-match works for a narrow slice of tasks. Everything else leaves you two options. A rubric that an LLM applies, or a human reading the outputs. LLM-as-judge scales, and it also inherits the same biases as the system under test, which is a real problem rather than a footnote. So I anchor the judge against a small human-labeled set first. If it disagrees with people there, it has no business scoring thousands of cases.\u003c/p\u003e\n\u003cp\u003eThe payoff is speed. Once the suite reflects reality you can refactor a pipeline hard, because the evals tell you within minutes what you broke. That is the whole advantage. A team that can answer \u0026#39;did that change help?\u0026#39; with evidence will outrun a team trading prompt tricks, and it will not be close.\u003c/p\u003e\n\u003cp\u003eHere is the rule I hold to. Write the eval before the feature feels done, not after it breaks in production.\u003c/p\u003e\n1a:[[\"$\",\"div\",null,{\"aria-hidden\":true,\"className\":\"pointer-events-none fixed inset-0 z-0\",\"children\":[[\"$\",\"$L13\",null,{\"density\":0.9}],[\"$\",\"div\",null,{\"className\":\"absolute inset-0\",\"style\":{\"background\":\"radial-gradient(60% 50% at 75% 10%, rgb(var(--accent) / 0.05), transparent 70%)\"}}],[\"$\",\"div\",null,{\"className\":\"absolute inset-0\",\"style\":{\"background\":\"radial-gradient(45% 40% at 12% 88%, rgb(var(--accent) / 0.06), transparent 70%)\"}}]]}],[\"$\",\"div\",null,{\"className\":\"relative z-10 flex min-h-svh flex-col\",\"children\":[[\"$\",\"main\",null,{\"id\":\"main-content\",\"className\":\"flex-1\",\"children\":[\"$\",\"div\",null,{\"className\":\"shell page-pad\",\"children\":[[\"$\",\"script\",null,{\"type\":\"application/ld+json\",\"dangerouslySetInnerHTML\":{\"__html\":\"{\\\"@context\\\":\\\"https://schema.org\\\",\\\"@type\\\":\\\"BlogPosting\\\",\\\"@id\\\":\\\"https://www.ashutosh887.in/writing/evals-are-the-product/#post\\\",\\\"headline\\\":\\\"Evals are the product\\\",\\\"description\\\":\\\"Ship an 
6LLM feature and the eval suite becomes the spec, whether you meant it to or not. Write it like one from the start.\\\",\\\"datePublished\\\":\\\"2026-06-12\\\",\\\"dateModified\\\":\\\"2026-06-12\\\",\\\"articleSection\\\":\\\"Evals\\\",\\\"keywords\\\":\\\"ai, llm, evals, machine-learning\\\",\\\"image\\\":\\\"https://www.ashutosh887.in/writing/evals-are-the-product/opengraph-image\\\",\\\"inLanguage\\\":\\\"en-IN\\\",\\\"url\\\":\\\"https://www.ashutosh887.in/writing/evals-are-the-product\\\",\\\"mainEntityOfPage\\\":{\\\"@type\\\":\\\"WebPage\\\",\\\"@id\\\":\\\"https://www.ashutosh887.in/writing/evals-are-the-product\\\"},\\\"author\\\":{\\\"@id\\\":\\\"https://www.ashutosh887.in/#person\\\"},\\\"publisher\\\":{\\\"@id\\\":\\\"https://www.ashutosh887.in/#person\\\"},\\\"isPartOf\\\":{\\\"@id\\\":\\\"https://www.ashutosh887.in/#website\\\"}}\"}}],[\"$\",\"script\",null,{\"type\":\"application/ld+json\",\"dangerouslySetInnerHTML\":{\"__html\":\"{\\\"@context\\\":\\\"https://schema.org\\\",\\\"@type\\\":\\\"BreadcrumbList\\\",\\\"itemListElement\\\":[{\\\"@type\\\":\\\"ListItem\\\",\\\"position\\\":1,\\\"name\\\":\\\"Home\\\",\\\"item\\\":\\\"https://www.ashutosh887.in\\\"},{\\\"@type\\\":\\\"ListItem\\\",\\\"position\\\":2,\\\"name\\\":\\\"Writing\\\",\\\"item\\\":\\\"https://www.ashutosh887.in/writing\\\"},{\\\"@type\\\":\\\"ListItem\\\",\\\"position\\\":3,\\\"name\\\":\\\"Evals are the product\\\",\\\"item\\\":\\\"https://www.ashutosh887.in/writing/evals-are-the-product\\\"}]}\"}}],[\"$\",\"article\",null,{\"children\":[[\"$\",\"$L16\",null,{\"href\":\"/writing\",\"prefetch\":false,\"className\":\"ghost-button\",\"children\":[[\"$\",\"$L17\",null,{\"ref\":\"$undefined\",\"iconNode\":\"$3:props:children:5:props:children:props:children:props:notFound:0:1:props:children:0:props:children:props:children:props:children:1:props:children:props:children:0:props:iconNode\",\"className\":\"lucide-arrow-left h-4 w-4\",\"strokeWidth\":1.5}],\"All writing\"]}],[\"$\",\"header\",null,{\"className\":\"mt-9 border-b border-hairline pb-8 sm:mt-12 sm:pb-10\",\"children\":[[\"$\",\"div\",null,{\"className\":\"flex flex-wrap items-center gap-2\",\"children\":[[\"$\",\"span\",null,{\"className\":\"chip px-3.5 py-1.5 text-sm border-accent/30 text-accent\",\"children\":\"Evals\"}],[\"$\",\"span\",null,{\"className\":\"chip px-3.5 py-1.5 text-sm\",\"children\":\"12 Jun 2026\"}],[\"$\",\"span\",null,{\"className\":\"chip px-3.5 py-1.5 text-sm\",\"children\":\"2 min read\"}]]}],[\"$\",\"h1\",null,{\"className\":\"mt-5 font-display text-4xl font-semibold leading-[1.05] tracking-tight text-balance text-ink md:text-5xl\",\"children\":\"Evals are the product\"}]]}],[\"$\",\"div\",null,{\"className\":\"post-body\",\"dangerouslySetInnerHTML\":{\"__html\":\"$26\"}}],\"$L27\"]}]]}]}],\"$L28\"]}]]\n27:[\"$\",\"footer\",null,{\"className\":\"mt-10 border-t border-hairline pt-8 sm:mt-14\",\"children\":[null,[\"$\",\"$L16\",null,{\"href\":\"/writing\",\"prefetch\":false,\"className\":\"ghost-button\",\"children\":[[\"$\",\"$L17\",null,{\"ref\":\"$undefined\",\"iconNode\":\"$3:props:children:5:props:children:props:children:props:notFound:0:1:props:children:0:props:children:props:children:props:children:1:props:children:props:children:0:props:iconNode\",\"className\":\"lucide-arrow-left h-4 w-4\",\"strokeWidth\":1.5}],\"All writing\"]}]]}]\n29:T518,M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z28:[\"$\",\"footer\",null,{\"className\":\"border-t border-hairline\",\"children\":[\"$\",\"div\",null,{\"className\":\"shell mx-auto flex w-full max-w-6xl flex-col items-center justify-between gap-3 py-6 pb-24 sm:flex-row lg:pb-6\",\"children\":[[\"$\",\"div\",null,{\"className\":\"flex flex-col gap-1\",\"children\":[\"$\",\"p\",null,{\"className\":\"mono-xs uppercase tracking-[0.14em] text-faint\",\"children\":[\"© \",[\"$\",\"span\",null,{\"children\":2026}],\" \",\"Ashutosh Jha\"]}]}],[\"$\",\"div\",null,{\"className\":\"flex flex-col items-center gap-3 sm:flex-row\",\"children\":[[\"$\",\"div\",null,{\"className\":\"flex items-center gap-3\",\"children\":[[\"$\",\"$L16\",null,{\"href\":\"/community\",\"className\":\"text-sm text-muted transition-colors duration-150 hover:text-ink\",\"children\":\"Community\"}],[\"$\",\"span\",null,{\"aria-hidden\":true,\"className\":\"h-4 w-px bg-hairline-strong\"}],[\"$\",\"$L16\",null,{\"href\":\"/contact\",\"className\":\"text-sm text-muted transition-colors duration-150 hover:text-ink\",\"children\":\"Get in touch\"}]]}],[\"$\",\"span\",null,{\"aria-hidden\":true,\"className\":\"hidden h-4 w-px bg-hairline-strong sm:block\"}],[\"$\",\"div\",null,{\"className\":\"flex items-center gap-3\",\"children\":[[[\"$\",\"a\",\"github\",{\"href\":\"https://github.com/ashutosh887\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"GitHub profile\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 496 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"$29\",\"children\":[]}
6]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}],[\"$\",\"a\",\"linkedin\",{\"href\":\"https://www.linkedin.com/in/ashutosh887\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"LinkedIn profile\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 448 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"M416 32H31.9C14.3 32 0 46.5 0 64.3v383.4C0 465.5 14.3 480 31.9 480H416c17.6 0 32-14.5 32-32.3V64.3c0-17.8-14.4-32.3-32-32.3zM135.4 416H69V202.2h66.5V416zm-33.2-243c-21.3 0-38.5-17.3-38.5-38.5S80.9 96 102.2 96c21.2 0 38.5 17.3 38.5 38.5 0 21.3-17.2 38.5-38.5 38.5zm282.1 243h-66.4V312c0-24.8-.5-56.7-34.5-56.7-34.6 0-39.9 27-39.9 54.9V416h-66.4V202.2h63.7v29.2h.9c8.9-16.8 30.6-34.5 62.9-34.5 67.2 0 79.7 44.3 79.7 101.9V416z\",\"children\":[]}]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}],\"$L2a\",\"$L2b\",\"$L2c\"],\"$L2d\"]}]]}]]}]}]\n2a:[\"$\",\"a\",\"twitter\",{\"href\":\"https://x.com/ashutosh887_\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"X (Twitter) profile\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 512 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z\",\"children\":[]}]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}]\n2b:[\"$\",\"a\",\"instagram\",{\"href\":\"https://instagram.com/ashutosh887_\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"Instagram profile\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 448 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"M224.1 141c-63.6 0-114.9 51.3-114.9 114.9s51.3 114.9 114.9 114.9S339 319.5 339 255.9 287.7 141 224.1 141zm0 189.6c-41.1 0-74.7-33.5-74.7-74.7s33.5-74.7 74.7-74.7 74.7 33.5 74.7 74.7-33.6 74.7-74.7 74.7zm146.4-194.3c0 14.9-12 26.8-26.8 26.8-14.9 0-26.8-12-26.8-26.8s12-26.8 26.8-26.8 26.8 12 26.8 26.8zm76.1 27.2c-1.7-35.9-9.9-67.7-36.2-93.9-26.2-26.2-58-34.4-93.9-36.2-37-2.1-147.9-2.1-184.9 0-35.8 1.7-67.6 9.9-93.9 36.1s-34.4 58-36.2 93.9c-2.1 37-2.1 147.9 0 184.9 1.7 35.9 9.9 67.7 36.2 93.9s58 34.4 93.9 36.2c37 2.1 147.9 2.1 184.9 0 35.9-1.7 67.7-9.9 93.9-36.2 26.2-26.2 34.4-58 36.2-93.9 2.1-37 2.1-147.8 0-184.8zM398.8 388c-7.8 19.6-22.9 34.7-42.6 42.6-29.5 11.7-99.5 9-132.1 9s-102.7 2.6-132.1-9c-19.6-7.8-34.7-22.9-42.6-42.6-11.7-29.5-9-99.5-9-132.1s-2.6-102.7 9-132.1c7.8-19.6 22.9-34.7 42.6-42.6 29.5-11.7 99.5-9 132.1-9s102.7-2.6 132.1 9c19.6 7.8 34.7 22.9 42.6 42.6 11.7 29.5 9 99.5 9 132.1s2.7 102.7-9 132.1z\",\"children\":[]}
6]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}]\n2c:[\"$\",\"a\",\"email\",{\"href\":\"mailto:[email protected]?subject=Hello%20from%20Portfolio\u0026body=Hi%20Ashutosh,%20I%20found%20your%20portfolio%20and%20would%20like%20to%20connect.\",\"target\":\"_blank\",\"rel\":\"noreferrer noopener\",\"aria-label\":\"Email Ashutosh\",\"className\":\"relative text-faint before:absolute before:-inset-3 before:rounded-full before:content-[''] transition-[color] duration-150 hover:text-ink\",\"children\":[\"$\",\"svg\",null,{\"stroke\":\"currentColor\",\"fill\":\"currentColor\",\"strokeWidth\":\"0\",\"viewBox\":\"0 0 512 512\",\"style\":{\"color\":\"currentColor\"},\"aria-hidden\":\"true\",\"children\":[\"$undefined\",[[\"$\",\"path\",\"0\",{\"d\":\"M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z\",\"children\":[]}]]],\"className\":\"$undefined\",\"height\":18,\"width\":18,\"xmlns\":\"http://www.w3.org/2000/svg\"}]}]\n2d:[\"$\",\"a\",null,{\"href\":\"/feed.xml\",\"className\":\"relative text-faint transition-colors duration-150 hover:text-ink before:absolute before:-inset-3 before:rounded-full before:content-['']\",\"aria-label\":\"RSS feed\",\"children\":[\"$\",\"svg\",null,{\"width\":\"14\",\"height\":\"14\",\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":\"2\",\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",null,{\"d\":\"M4 11a9 9 0 0 1 9 9\"}],[\"$\",\"path\",null,{\"d\":\"M4 4a16 16 0 0 1 16 16\"}],[\"$\",\"circle\",null,{\"cx\":\"5\",\"cy\":\"19\",\"r\":\"1\"}]]}]}]\n1f:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"2\",{\"name\":\"theme-color\",\"content\":\"#0a0a0a\"}]]\n1d:null\n2e:T7fb,Hire Ashutosh Jha,Ashutosh Jha for hire,Hire Software Engineer Bengaluru,Hire Full Stack Developer India,Hire AI Engineer,Hire Cloud Engineer,Hire Web3 Developer,Ashutosh Jha,Ashutosh Jha Software Engineer,Ashutosh Jha Full Stack Developer,Ashutosh Jha AI Developer,Ashutosh Jha Web3 Developer,Ashutosh Jha Portfolio,Ashutosh Jha GitHub,Ashutosh Jha LinkedIn,ashutosh887,Software Engineer,Full Stack Developer,Full Stack Engineer,AI Engineer,AI and Full Stack Engineer,Infrastructure Engineer,Cloud Engineer,Machine Learning Engineer,Web3 Developer,Blockchain Developer,Developer Relations Engineer,Frontend Developer,Backend Developer,React Developer,Next.js Developer,Node.js Developer,TypeScript Developer,Python Developer,Go Developer,OpenAI Developer,GPT-4 Developer,Solana Developer,React.js,Next.js,Node.js,TypeScript,JavaScript,Python,Go,PostgreSQL,MongoDB,Redis,Docker,Kubernetes,AWS,Amazon EC2,Amazon S3,Amazon Aurora,Aurora DSQL,Google Cloud,Google Cloud Run,ClickHouse,Observability,OpenAI API,GPT-4 API,Google Gemini,Solana,Anchor Framework,Smart Contracts,Web3,Blockchain,REST API,WebSockets,Microservices,Insitu Engineer,AI Infrastructure Engineer,LLM Engineer,Agent Systems Engineer,RAG Engineer,South Park Commons Engineer,Transak Developer,CubeAPM Engineer,Stub,NeverLose,FinQuery,Evolv,WinterArc,StudioCast,saathi,ClickLiv,Plumb,Darwin,ClawGuard,Stoq,verdex,BridgeRadar,moodcast,FeelTheWeb,depextract,ethsapien,PayFlow,Portkey AI Builder Challenge Winner,Pine Labs AI Hackathon Finalist,Ethereum Payment Workflows,Prompt Engineering Platform,AlivePing,SafeVoice,ShotLock,CareerFit,LaunchKit,CivicLens,Voice AI,CIBA,x402,Cross-chain,Bridging risk,Bengaluru Software Engineer,Bengaluru Developer,Karnataka Developer,India Software Engineer,India Developer,Remote Software Engineer,AI-powered a
6pplications,AI chatbot developer,Slack bot developer,WhatsApp bot developer,SDK developer,Developer tools,Browser extension developer,Real-time applications,Scalable applications,Performance optimization,System design,API development21:[[\"$\",\"title\",\"0\",{\"children\":\"Evals are the product - Ashutosh Jha\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"Ship an LLM feature and the eval suite becomes the spec, whether you meant it to or not. Write it like one from the start.\"}],[\"$\",\"meta\",\"2\",{\"name\":\"application-name\",\"content\":\"Ashutosh Jha Portfolio\"}],[\"$\",\"link\",\"3\",{\"rel\":\"author\",\"href\":\"https://www.ashutosh887.in\"}],[\"$\",\"meta\",\"4\",{\"name\":\"author\",\"content\":\"Ashutosh Jha\"}],[\"$\",\"link\",\"5\",{\"rel\":\"manifest\",\"href\":\"/manifest.webmanifest\",\"crossOrigin\":\"$undefined\"}],[\"$\",\"meta\",\"6\",{\"name\":\"keywords\",\"content\":\"$2e\"}],[\"$\",\"meta\",\"7\",{\"name\":\"referrer\",\"content\":\"origin-when-cross-origin\"}],[\"$\",\"meta\",\"8\",{\"name\":\"creator\",\"content\":\"Ashutosh Jha\"}],[\"$\",\"meta\",\"9\",{\"name\":\"publisher\",\"content\":\"Ashutosh Jha\"}],[\"$\",\"meta\",\"10\",{\"name\":\"robots\",\"content\":\"index, follow\"}],[\"$\",\"meta\",\"11\",{\"name\":\"googlebot\",\"content\":\"index, follow, max-video-preview:-1, max-image-preview:large, max-snippet:-1\"}],[\"$\",\"meta\",\"12\",{\"name\":\"category\",\"content\":\"Technology\"}],[\"$\",\"meta\",\"13\",{\"name\":\"classification\",\"content\":\"Portfolio Website\"}],[\"$\",\"meta\",\"14\",{\"name\":\"apple-mobile-web-app-capable\",\"content\":\"yes\"}],[\"$\",\"meta\",\"15\",{\"name\":\"apple-mobile-web-app-status-bar-style\",\"content\":\"black-translucent\"}],[\"$\",\"meta\",\"16\",{\"name\":\"apple-mobile-web-app-title\",\"content\":\"Ashutosh Jha\"}],[\"$\",\"meta\",\"17\",{\"name\":\"mobile-web-app-capable\",\"content\":\"yes\"}],[\"$\",\"meta\",\"18\",{\"name\":\"msapplication-TileColor\",\"content\":\"#0a0a0a\"}],[\"$\",\"meta\",\"19\",{\"name\":\"profile:first_name\",\"content\":\"Ashutosh\"}],\"$L2f\",\"$L30\",\"$L31\",\"$L32\",\"$L33\",\"$L34\",\"$L35\",\"$L36\",\"$L37\",\"$L38\",\"$L39\",\"$L3a\",\"$L3b\",\"$L3c\",\"$L3d\",\"$L3e\",\"$L3f\",\"$L40\",\"$L41\",\"$L42\",\"$L43\",\"$L44\",\"$L45\",\"$L46\",\"$L47\",\"$L48\",\"$L49\",\"$L4a\",\"$L4b\",\"$L4c\",\"$L4d\"]\n4e:I[27201,[\"/_next/static/immutable/chunks/1tf2pn9278k7y.js\"],\"IconMark\"]\n2f:[\"$\",\"meta\",\"20\",{\"name\":\"profile:last_name\",\"content\":\"Jha\"}]\n30:[\"$\",\"meta\",\"21\",{\"name\":\"profile:username\",\"content\":\"ashutosh887\"}]\n31:[\"$\",\"meta\",\"22\",{\"name\":\"og:profile:first_name\",\"content\":\"Ashutosh\"}]\n32:[\"$\",\"meta\",\"23\",{\"name\":\"og:profile:last_name\",\"content\":\"Jha\"}]\n33:[\"$\",\"link\",\"24\",{\"rel\":\"canonical\",\"href\":\"https://www.ashutosh887.in/writing/evals-are-the-product\"}]\n34:[\"$\",\"link\",\"25\",{\"rel\":\"alternate\",\"type\":\"application/rss+xml\",\"href\":\"https://www.ashutosh887.in/feed.xml\"}]\n35:[\"$\",\"meta\",\"26\",{\"property\":\"og:title\",\"content\":\"Evals are the product - Ashutosh Jha\"}]\n36:[\"$\",\"meta\",\"27\",{\"property\":\"og:description\",\"content\":\"Ship an LLM feature and the eval suite becomes the spec, whether you meant it to or not. Write it like one from the start.\"}]\n37:[\"$\",\"meta\",\"28\",{\"property\":\"og:url\",\"content\":\"https://www.ashutosh887.in/writing/evals-are-the-product\"}]\n38:[\"$\",\"meta\",\"29\",{\"property\":\"og:image\",\"content\":\"https://www.ashutosh887.in/writing/evals-are-the-product/opengraph-image?0c852efdf562a8d4\"}]\n39:[\"$\",\"meta\",\"30\",{\"property\":\"og:image:type\",\"content\":\"image/png\"}]\n3a:[\"$\",\"meta\",\"31\",{\"property\":\"og:image:width\",\"content\":\"1200\"}]\n3b:[\"$\",\"meta\",\"32\",{\"property\":\"og:image:height\",\"content\":\"630\"}]\n3c:[\"$\",\"meta\",\"33\",{\"property\":\"og:type\",\"content\":\"article\"}]\n3d:[\"$\",\"meta\",\"34\",{\"property\":\"article:published_time\",\"content\":\"2026-06-12\"}]\n3e:[\"$\",\"meta\",\"35\",{\"property\":\"article:modified_time\",\"content\":\"2026-06-12\"}]\n3f:[\"$\",\"meta\",\"36\",{\"property\":\"article:author\",\"content\":\"https://www.ashutosh887.in\"}]\n40:[\"$\",\"meta\",\"37\",{\"property\":\"article:tag\",\"content\":\"ai\"}]\n41:[\"$\",\"meta\",\"38\",{\"property\":\"article:tag\",\"content\":\"llm\"}]\n42:[\"$\",\"meta\",\"39\",{\"property\":\"article:tag\",\"content\":\"evals\"}]\n43:[\"$\",\"meta\",\"40\",{\"property\":\"article:tag\",\"content\":\"machine-learning\"}]\n44:[\"$\",\"meta\",\"41\",{\"name\":\"twitter:card\",\"content\":\"summary_large_image\"}]\n45:[\"$\",\"meta\",\"42\",{\"name\":\"twitter:title\",\"content\":\"Evals are the product - Ashutosh Jha\"}]\n46:[\"$\",\"meta\",\"43\",{\"name\":\"twitter:description\",\"content\":\"Ship an 
6LLM feature and the eval suite becomes the spec, whether you meant it to or not. Write it like one from the start.\"}]\n47:[\"$\",\"meta\",\"44\",{\"name\":\"twitter:image\",\"content\":\"https://www.ashutosh887.in/writing/evals-are-the-product/opengraph-image?0c852efdf562a8d4\"}]\n48:[\"$\",\"meta\",\"45\",{\"name\":\"twitter:image:type\",\"content\":\"image/png\"}]\n49:[\"$\",\"meta\",\"46\",{\"name\":\"twitter:image:width\",\"content\":\"1200\"}]\n4a:[\"$\",\"meta\",\"47\",{\"name\":\"twitter:image:height\",\"content\":\"630\"}]\n4b:[\"$\",\"link\",\"48\",{\"rel\":\"icon\",\"href\":\"/icon?29b4dc8a27dd18bc\",\"alt\":\"$undefined\",\"type\":\"image/png\",\"sizes\":\"512x512\"}]\n4c:[\"$\",\"link\",\"49\",{\"rel\":\"apple-touch-icon\",\"href\":\"/apple-icon?f0d5e0f0fa426977\",\"alt\":\"$undefined\",\"type\":\"image/png\",\"sizes\":\"180x180\"}]\n4d:[\"$\",\"$L4e\",\"50\",{}]\n"])</script>
6</body></html>

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.