
Build a working prototype in one focused AI session from idea to live
You'll have a functioning application or feature you demoed to someone, proving your idea works without weeks of iteration.
What you'll make
Live Prototype Demo
- app.py or index.html — the main application file: what to include
- test_basic.py — verification tests that pass: what to include
- demo_evidence.md — screenshot or video of it working: what to include
Upload your main code file, your test file, and evidence (screenshot or brief video) that someone else saw it work
The 3 parts
Each part ends with a check you can see.
Scope One Testable Feature
Pick a single, concrete feature you can verify works and demo to someone in under 4 hours
Done when
You have one feature described in 2-3 sentences with a clear 'it works when...' test you can run
Build with Verification Checkpoints
Use AI to generate your feature while testing functionality at each step rather than waiting until the end
Done when
You have working code that passes at least 3 specific tests you wrote and ran during development
Ship and Demo Live
Deploy your working prototype and demonstrate it to another person to prove it actually functions
Done when
You have deployed your prototype and shown it working to at least one other person, with evidence of their reaction
Capstone: you put together your Live Prototype Demo.
Where this helps
An elective: a single lesson that sits outside rtwo's job certificates and doesn't count toward one.
About this lesson
What you'll be able to do
- Ship a working prototype built primarily with AI in one 3-4 hour session
- Apply a verification framework that catches AI errors before they break your app
- Know when to trust AI output vs when to override it in a development context
- Have a reusable workflow for turning ideas into deployed prototypes fast
Who it's for
- Anyone who's wondered if they could build software with AI but worried about quality
- People comfortable following technical instructions even if they don't write code from scratch
- Product managers or designers who want to prototype their own ideas without waiting for engineering
What it won't cover
- Production-ready security or scalability hardening
- Traditional software engineering practices like version control or code architecture
- Choosing between different AI coding platforms
- Building complex multi-service applications
Skills you'll practise
- Structured verification of AI-generated code
- Scope management for rapid prototyping
- Progressive testing strategy
- AI output quality assessment