Skip to content
Manoj Gavi

Software Engineer / AI agents · Automation · Cloud

Hi, I'm Manoj Gavi.

Software engineer building AI agents, workflow automation, and full-stack applications.

I build AI systems that connect to real data, real tools, and real workflows — and I make them easy to try.

View projects Resume

Try the live projects

system.flow
  1. 01
    Data
    Messages, documents, records
  2. 02
    Intelligence
    Validate · structure · retrieve evidence
  3. 03
    Automation
    Agent picks tools, drafts the next step
  4. 04
    Action
    Grounded answer · human approval
evidence-first · tools over guesses · humans approve changes

I build intelligent systems that turn complex workflows into practical, usable software.

  • Data first

    Validate and structure the data before any AI touches it.

  • Evidence, not guesses

    Answers cite the records they came from — or say “I don't know.”

  • Humans approve

    AI suggests. People decide anything that changes data.

Featured projects

Two working applications you can try.

Each one has a plain-language explanation, a step-by-step diagram, and a public demo account.

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

Architecture, simply

Data in. Evidence out.

You don't need to understand AI to follow these. Each box is one step; the last box is what you get.

Healthcare Intelligence Platform

Messy messages become clean records; the agent answers with citations.

  1. Data
  2. Validation
  3. FHIR
  4. AI Agent
  5. Tools + RAG
  6. Evidence
  7. Answer

PersonalOps AI

Documents become organised records; the agent suggests, you approve.

  1. Documents
  2. Extraction
  3. Database
  4. RAG
  5. AI Agent
  6. Suggested action
  7. Your approval
Read the plain-language explanation

Technical capabilities

What I work with

Only tools used in these projects. Hover or focus any item for a plain-English meaning.

AI & agents

Making AI follow steps, use tools, and show its sources.

  • LangGraph — Runs the AI agent as a clear, step-by-step workflow. Used in: Healthcare, PersonalOps.
  • RAG — The AI looks up relevant documents first, then answers from them. Used in: Healthcare, PersonalOps.
  • Tool calling — The agent uses small, well-defined functions to fetch data. Used in: Healthcare, PersonalOps.
  • LLM APIs — Optional language models (Anthropic, OpenAI, AWS Bedrock) for wording answers. Used in: Healthcare, PersonalOps.
  • MCP — A standard way for other AI tools to use the platform's functions. Used in: Healthcare.
  • Evaluation — A test set of questions that scores answers for accuracy and grounding. Used in: Healthcare, PersonalOps.

Backend & data

Reliable APIs and a clean data layer underneath the AI.

  • Python — Main language for the backends. Used in: Healthcare, PersonalOps.
  • FastAPI — Framework for the web APIs. Used in: Healthcare, PersonalOps.
  • PostgreSQL — The main database. Used in: Healthcare, PersonalOps.
  • pgvector — Lets the database search by meaning, not only exact words. Used in: Healthcare, PersonalOps.
  • SQLAlchemy — Connects Python code to the database safely. Used in: Healthcare, PersonalOps.
  • REST APIs — Standard web endpoints the frontends talk to. Used in: Healthcare, PersonalOps.

Frontend

Interfaces that make complex systems easy to explore.

  • React — Library for building the user interfaces. Used in: Healthcare, PersonalOps, This site.
  • TypeScript — JavaScript with types, which catches mistakes early. Used in: Healthcare, PersonalOps, This site.
  • Next.js — React framework. Used in: PersonalOps, This site.
  • Tailwind CSS — Styling system. Used in: Healthcare, PersonalOps, This site.

Healthcare data

The formats hospitals and clinics actually exchange.

  • HL7 v2 — The classic message format hospital systems send each other. Used in: Healthcare.
  • C-CDA — A standard format for clinical documents like visit summaries. Used in: Healthcare.
  • FHIR R4 — The modern standard for storing and sharing health records. Used in: Healthcare.

Cloud & delivery

Packaging and shipping software cheaply and repeatably.

  • Docker — Packages each service so it runs the same everywhere. Used in: Healthcare, PersonalOps.
  • AWS — Optional Bedrock models in both apps; Route 53 DNS for this site. Used in: Healthcare, PersonalOps, This site.
  • Vercel & Render — Hosting for this site, the app frontends, and the app APIs. Used in: Healthcare, PersonalOps, This site.
  • Terraform — Describes infrastructure — here, the site's DNS — as code. Used in: This site.
  • GitHub Actions — Checks every change to this site before it ships. Used in: This site.

“AI should solve a real problem. It shouldn't be added just because a project uses AI.”

About

Practical AI, connected to real work.

I'm a software engineer who builds full-stack applications where AI does useful, checkable work. My recent projects take messy inputs — healthcare messages, personal documents — turn them into clean, structured data, and put an AI agent on top that answers questions with evidence and asks before it changes anything.

The Healthcare Intelligence Platform tackles a hard, regulated-style domain. PersonalOps AI applies the same architecture to an everyday problem. Together they show how I approach any workflow.

Read the engineering story

Resume

The one-page version

Experience, skills, and education in a single document.

Resume coming soon

Contact

Let's build something useful.

Hiring, collaborating, or just curious how something works? I'm happy to talk.

Get in touch