Mission 10 of 12
Build a Number Guessing Game
Build a number guessing game with an AI twist - the AI generates smart hints and reacts to the player. Connect a real AI API (OpenAI or Claude), handle its responses, and design for uncertainty.
By the end of this mission: “I can integrate a real AI API into a product, handle its output, and design for uncertainty.”
The tech stack for this mission
What you learn, checkpoint by checkpoint
Checkpoint A
Build the game UI and core guessing logic
- Build the game UI - input, feedback area and controls in React
- Implement the core guessing logic and game state
- Set up an Express endpoint to talk to the AI securely
Checkpoint B
Wire in the AI API for hints and reactions
- Call the OpenAI or Claude API from your server-side route
- Turn the game state into a good prompt for hints and reactions
- Render the AI response in the UI and handle the loading state
Checkpoint C
Handle errors and edge cases, then deploy
- Handle empty, slow and error responses from the AI gracefully
- Guard against bad or unsafe input reaching the API
- Test against real play-throughs, then deploy
AI companion mode · AI as Product
AI runs inside what you build
AI lives inside the product you build. Treat its output as untrusted - handle errors, evaluate quality, design for uncertainty.
What proves you’re done
Deployed AI-powered guessing game + evaluation notes
Every mission ships something real and public. If you can’t explain it, you can’t submit it.
Reading is not building.
This mission is part of the paid 12-week programme - but the way we teach is free to try. The free trial puts you inside Sigmo, the learning portal our students use daily, with the 6 Projects in 6 Days precourse: real projects, real code, published to your own GitHub.
Start the free trialReady for the real thing?
The AI-Native Software Development Programme - all 12 missions with a live cohort, daily Buildroom, and mentors watching your back.