Overview
What this challenge is about.
Implement Connect-Four (7-column, 6-row board) in Python plus a minimax agent with alpha-beta pruning, configurable search depth, and a simple heuristic evaluation function for non-terminal states. Build a web UI (Streamlit or Flask) that lets a student play against the agent. Profile the agent at depths 4, 6, and 8 to show the depth-vs-think-time trade-off live. Write a 30-minute lesson plan covering 'what is search', 'what is minimax', 'why alpha-beta helps', and a 5-question student worksheet.
The Brief
What you'll do, and what you'll demonstrate.
Ship a Connect-Four minimax agent with a classroom UI and a teacher-ready 30-minute lesson plan.
Earning criteria — what you'll demonstrate
- Implement minimax with alpha-beta pruning on a classic two-player game
- Design a non-terminal heuristic evaluation function
- Profile search depth vs. compute trade-offs
- Translate an AI demo into a teacher-deliverable lesson
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
AI Engineer
Shipping a small AI app end-to-end (algorithm plus UI plus docs) is the AI engineer's first-week deliverable at any startup.
This challenge sharpens
- minimax
- alpha-beta-pruning
- python
AI Product Designer
Wrapping a game-tree agent in a UI a teenager can use surfaces the core product-design skill of making AI feel comprehensible.
This challenge sharpens
- user-interface-design
- educational-content-design
- game-playing-ai
AI Product Manager
Translating an AI capability into a teacher-deliverable lesson is exactly the AI PM skill of bridging tech to a non-technical audience.
This challenge sharpens
- educational-content-design
- user-interface-design
- game-playing-ai