Analyzes sent-email history to model tone, formality, and structure, then generates reply drafts that mirror the user's communication style.
Things I've built.
11projects & counting
AI that does something useful. Products that connect the dots. A few experiments along the way.
Start here. (04 projects)
Four builds that show how I connect AI, architecture, and a useful interface.
Generates dual-perspective prosecution and defense arguments from incident descriptions, grounded in Indian law and citation-aware retrieval.
Step-by-step DSA walkthroughs where JSON state objects drive synchronized SVG animation, variable tracing, and code highlighting.
A research assistant that turns a question and a set of PDFs or web pages into a grounded answer, then checks every claim in it against the retrieved evidence.
Under the hood. (04 projects)
Evaluation, security workflows, and the infrastructure behind AI products.
A SIEM alert-triage service built with teammates in 24 hours: it scores incoming security alerts, explains every score, and suggests a first response.
A document AI pipeline that parses pages into verified blocks, extracts fields against your own schema, and cites every value back to the exact region of the page.
A local voice-cloning app: record a short clip in the browser, type what it should say, and get speech in that voice from Qwen3-TTS running on a Mac.
A consent-first personal AI agent: a central agent routes requests to specialist agents for finance and creator work, and the server checks stored consent before any of them reads your data.
Made to be used. (03 projects)
Learning products and small tools for everyday engineering.
End-to-end learning platform with sandboxed code execution, in-browser IDE, AI hints, real-time progress tracking, and gamification.
A personal-finance app for salaried people in India that answers one question: how much can I still spend before payday?
Node.js CLI and programmable API that finds and safely terminates zombie processes occupying local development ports.