Skip to content
Manoj Gavi

Projects

Two live applications.

Each project opens in its own tab with a public demo account. Start with the plain-language page if you'd like the story first.

Project 01Live demo

Healthcare Intelligence Platform

Healthcare interoperability + AI workflow automation

A platform that receives healthcare data, checks it, cleans it into one consistent format, and uses an AI agent to find and explain relevant information — always pointing to the evidence it used.

How it flows

  1. Data
  2. Validation
  3. FHIR
  4. AI Agent
  5. Tools + RAG
  6. Evidence
  7. Answer
  • HL7 — The classic message format hospital systems send each other.
  • C-CDA — A standard format for clinical documents like visit summaries.
  • FHIR — The modern standard for storing and sharing health records.
  • Validation — Checking data for missing or invalid information.
  • RAG — The AI searches documents first, then answers using what it found.
  • LangGraph — Runs the AI agent as a clear, step-by-step workflow.
  • AI Agent — An AI that decides which tools to use to answer a question.
  • MCP — A standard way for other AI tools to use the platform's functions.
  • Evaluation — A test set that scores the agent's answers.
Open live demo (opens in a new tab)View project How it works Demo login
Project 02Live demo

PersonalOps AI

AI-powered personal information and productivity assistant

A personal AI assistant that reads your documents, pulls out the useful details, answers questions with evidence, and helps keep track of bills, subscriptions, warranties, and deadlines — but never changes anything without your approval.

How it flows

  1. Documents
  2. Extraction
  3. Database
  4. RAG
  5. AI Agent
  6. Suggested action
  7. Your approval
  • LangGraph — Runs the AI agent as a clear, step-by-step workflow.
  • RAG — The AI searches your documents first, then answers using what it found.
  • Document extraction — Reading text and key details out of PDFs, Word files, and more.
  • Tool calling — The agent uses small, well-defined functions to look things up.
  • PostgreSQL — The database where your organised records are stored.
  • Vector search — Searching by meaning, not only exact words.
  • FastAPI — The framework the backend API is built with.
  • Next.js — The framework the web interface is built with.
  • Human-in-the-loop — The AI suggests; you approve before anything changes.
Open live demo (opens in a new tab)View project How it works Demo login

Why these projects

Two problems. One engineering approach.

Different domains, same idea: get the data right, let the AI use real tools, show the evidence, and keep a human in control.

Healthcare Intelligence Platform

Healthcare data is spread across formats that don't agree with each other.

Solves

  • Healthcare data complexity
  • Interoperability between systems
  • Finding the right information
  • Automating care-coordination checks

PersonalOps AI

Personal information is buried in receipts, bills, and emails.

Solves

  • Personal information overload
  • Searching across documents
  • Never missing a deadline
  • Turning findings into tasks — with approval

Common engineering

  • AI agents

    Step-by-step workflows, not one big guess

  • RAG

    Look it up first, then answer

  • Tool calling

    Small, typed functions the agent can use

  • APIs

    Clean FastAPI backends

  • Data processing

    Validate and structure before AI touches it

  • Evaluation

    Test sets that score the answers

  • Observability

    Traces of every step and tool call

  • Human-in-the-loop

    People approve what matters