How this works

AI assistant for Dhavan’s published portfolio material. Answers can be incomplete or wrong, so do not submit confidential code or data.

Your questions go through Hugging Face, and a model run by DeepInfra writes the answers. Chats may be retained for about 30 days to operate, debug and improve the assistant; DynamoDB TTL deletion is approximate. Cal.com handles call bookings. Details are in the privacy policy.

Use the suggested questions or ask about published projects, credentials, and engagements.

Projects / Production RAG Assistant

An AI assistant you can test right now.

The assistant on this site answers questions about my work from published evidence. It runs on AWS and Cloudflare, with rate limits and a budget reserved before each paid call.

Book a free call

Dhavan Shah You work with the person who built it. The first 30 minute call is free, and if I can’t help, I say so before you pay anything.

Running on this siteAWS and Cloudflare
Retrieval
BM25 plus vector
Rate limits
5 a minute, 20 an hour
Paid calls
Budget reserved first
Budget store down
Fails closed

StatusLive

A demo chatbot can invent answers, stall or get expensive.

Answer quality depends on production behavior too: latency, citations, rate limits, monitoring and cost control.

  • “Will it make things up?”

    Grounded, then checked

    It retrieves published evidence first, generates once, then verifies protected claims before committing the final answer.

  • “Could someone run up the bill?”

    Budget reserved before each paid call

    The worst case is reserved against daily and monthly caps before any paid call. If the budget store is down, it fails closed.

  • “Could it be abused?”

    Limits at the edge and in the app

    A Cloudflare Worker and firewall, IP rate limits, body size limits and a kill switch, plus fixed rate windows in the app.

  • “Will people sit waiting for an answer?”

    Streamed as it’s written

    Drafts stream as they’re written and stay provisional. Only the verified final answer is committed.

Answer quality depends on production behavior too.

How it works: retrieve, generate, verify.

Published evidence first, one generation, and a check before anything is final.

1 · Retrieve

Two kinds of search

BM25 and vector similarity, fused with reciprocal rank fusion, over a validated index.

2 · Generate

A streamed draft

System prompt, evidence and the visitor’s question produce a draft, shown as provisional.

3 · Verify

Then commit

Protected claims are verified before the final answer replaces the draft.

How it’s built.

The path from a visitor’s question to a verified answer.

browserCloudflare Pages chat UIedgeCloudflare Worker: WAF, rate limits, kill switchfunction URLAWS Lambda with response streamingappFastAPI: rate limit, budget reservationretrievalBM25 + vector, fused with RRFindexversioned S3 bundle, loaded on cold startstreamsearching, token, final or error

How it’s run

AWS CDK for infrastructure, and GitHub Actions for offline tests, security checks and deploys with a live smoke test. Failure metrics and alarms go to CloudWatch.

What’s stored

Visitor prompt text isn’t written into metric dimensions. Accepted questions and answers may be kept for about 30 days for debugging.

Before you get in touch.

Can you build one like this for us?
Yes. This is useful for teams replacing demo chatbots with grounded assistants that need answer discipline and operating limits.
Can it be wrong?
Yes. AI can be wrong, so don’t share confidential data with it. Its answers are checked against published evidence, and it’s built to hold back what it can’t verify.
What about speed?
End to end times depend on cold starts and the provider. Live smoke tests check the first streamed and final events, rather than quoting a fixed number.
How do we start?
Send a short description of the workflow and what is blocking it. I reply within one business day. The first 30 minute call is free, and there’s no obligation until you approve the Diagnostic.

Tell me about the assistant you want to put in front of customers.

The first 30 minute call is free, and I reply within one business day.

Book a free call

How engagements work · Back to Projects