🧠 Feynman AI Tutor — Python / Streamlit

Learn any topic for real, using Richard Feynman's technique. The AI explains it in plain words, asks you to teach it back, finds your blind spots, then re-explains them. Built with Python + Streamlit for the Built with Python Hackathon (CS4Everyone, 2026).

What it does

A Streamlit web app that runs the 4 steps of the Feynman Technique:

1. Explain it simply — pick a topic and depth; the app returns a plain explanation + a real-life analogy + key points.
2. Teach it back — you explain it in your own words.
3. Find the gaps — the app scores your understanding (0–100) and lists what you got right vs. missed.
4. Re-simplify — it re-teaches only your gaps.

Plus: comprehension questions, one-click export to a Markdown study note, and a Demo mode that runs with zero setup.

How Python was used

• Streamlit builds the entire UI and handles state (st.session_state), inputs, buttons, progress bar, and the download button — all in pure Python.
• requests calls the Google Gemini REST API and requests structured JSON (responseMimeType: application/json); a small Python parser (_parse_json) defensively recovers the JSON so the UI never breaks on a messy response.
• The Feynman prompts and the Demo-mode content/grading logic are plain Python functions, so the whole 4-step flow works even without an API key.

Run locally

pip install -r requirements.txt
streamlit run app.py

Opens at http://localhost:8501. It starts in Demo mode — no key needed.

Use real AI (any topic)

Get a free key at Google AI Studio, open the sidebar → Live AI (Gemini) → paste the key. The key stays in your Streamlit session and is only used to call Google directly.

Deploy (optional)

Push this repo to GitHub and deploy free on Streamlit Community Cloud (sign in with GitHub → pick the repo → app.py).

Files

• app.py — the whole app
• requirements.txt — streamlit, requests
• README.md — this file

License

MIT