Cyber & AI Security · AI Red Team
Own it end to end. Bigger projects you design, run and present like a professional.
Task 1 of 2
Multi-step testing of a real AI app.
What to do
Run a full test of an AI app you built or have permission to test, using long conversations, role-play, unusual formats and edge cases. Deliver a findings report with severity ratings.
You’ll make
Done looks like
A findings report with severity ratings.
Task 2 of 2
Track AI quality across versions.
What to do
Build a pipeline that generates test inputs, sends them to an AI app, scores the answers, and tracks the pass rate across prompt or model versions.
You’ll make
Done looks like
A pipeline that tracks pass rate across versions.
Learn before you build
Free course
Free courses on AI fluency and building with Claude, with certificates.
Free tool
Open-source tool to test prompts and AI apps against test cases.
Free tool
Public AI and data challenges to practise on.
Article guide
Real cases of AI going wrong, useful for review and testing.
Article guide
How to design AI products people understand and trust.