Project 02 · Live public AI
Ask AI
A public chatbot at ask.shraddhayeolekar.com that answers questions about my work using only my resume and GitHub projects, and cites its sources.
- Key decision
- Run the cheapest, most predictable guardrail before the model.
- Why
- A keyword filter refuses risky questions (salary, comparisons with other people, protected-class topics, jailbreak attempts) without calling Gemini. It runs before the five-a-day rate limit, so a refused question doesn't use up a visitor's quota. After the model, citations that don't match a real source are dropped.
- Gave up
- Some fair questions get refused by a blunt keyword list. For a bot that speaks in my name, I'd rather refuse a fair question than answer a risky one.
How it's built
Everything except the model and the GitHub content runs on Cloudflare: one Worker, with storage, spam protection and deployment from the same platform.
| Piece | What it does |
|---|---|
| Worker | Receives each question, runs the guardrails in order, calls Gemini and checks the citations. Everything else falls through to the static page. |
| KV | Three jobs: the kill-switch flag, a per-visitor daily counter that expires after about a day, and the cached GitHub READMEs. |
| D1 | Logs every question and answer, and whether the pre-filter blocked it, so real traffic can be reviewed. |
| Turnstile | Spam check. The Worker verifies the token server-side before the question goes any further. |
| context.md | The resume and project notes, bundled into the Worker at deploy time. |
| GitHub READMEs | Four project write-ups fetched live and cached for 24 hours, so they stay current without a redeploy. |
| Gemini 2.5 Flash | Answers from the provided sources only, returning structured JSON: the answer, its citations and a "grounded" flag. |
| Workers Builds | Builds and deploys automatically on every push to main. API keys live in Cloudflare's secrets, not in the code. |