Applied AI systems designed, built, and deployed end to end. 4 projects so far.
MediScribe — AI Clinical Documentation Assistant
Turns typed or dictated consultation notes into structured medical summaries, action items, and patient-ready letters — in 19 languages.
Clinicians lose real time after every visit writing up notes, follow-ups, and patient communication — often duplicated across languages for non-native speakers. MediScribe takes typed or voice-dictated notes and generates a clinical summary, a clear action-item list, and a patient-facing email, with one-click translation into 19 languages.
Fin-Ops Travel Planner — Multi-Agent Trip Budgeting Assistant
A CrewAI crew — Flight + Forex Specialist, Travel Budget Profiler, and a Fin-Ops Travel Planner — coordinates over MCP tools to produce a day-by-day itinerary and full budget breakdown that stays within a set total.
Planning international travel usually means juggling separate tabs for flight prices, currency conversion, and daily budget guesswork with no single view of whether the trip is actually affordable. This crew runs sequentially: a Flight + Forex Specialist pulls cost context through MCP tools, a Travel Budget Profiler allocates a daily spending plan, and a Fin-Ops Travel Planner agent assembles both into a day-by-day itinerary with a final budget table — for example, a 7-day Paris trip on a $4,000 total budget, broken down to accommodation, food, transport, and entertainment per day.
Litigation Prep Assistant — Multi-Step RAG Pipeline
A production-style monorepo that extracts case facts, retrieves grounding statutes, drafts strategy documents, and reviews its own output end to end.
Litigation prep involves extracting relevant facts from case materials, grounding arguments in the right statutes, and drafting strategy documents — usually a slow, manual research process. This system runs a multi-step LLM pipeline (extraction → RAG-grounded strategy generation → drafting → automated quality review) behind an authenticated web app, structured as a real product rather than a notebook demo.
Digital Twin — Conversational AI About Me
An AI twin recruiters can talk to directly about my background, skills, and projects — grounded in my actual experience rather than generic chat.
Recruiters and hiring managers often just want a quick answer, not a full conversation. This project is a conversational digital twin, grounded in my actual experience, that can answer questions about my background and projects directly.
A newer version — serverless on AWS, built with Terraform and GitHub Actions — is deployed and being finalized; link coming soon.