Learning paths

Pick a track, follow the steps

The lab has hundreds of pages; these four tracks put them in the right order for your role. Scenario progress is saved in your browser — no account.

Start Here: How AI Systems Actually Work

Anyone — no technical background needed

Build an intuition for what's inside a modern AI assistant, one layer at a time, and see your first thing-goes-wrong story.

7 steps · ~43 min0/2 scenarios done

AI Risk Practitioner Track

Risk, governance, security & compliance professionals

Work through the OWASP-aligned threat landscape with hands-on incidents, mapping each to root causes, controls, and frameworks (OWASP, ATLAS, NIST AI RMF).

9 steps · ~68 min0/5 scenarios done

Agentic & Multi-Agent Security

Engineers and security practitioners building agents

Go deep on the hardest surface in modern AI: autonomous agents, tools, MCP integrations, and teams of agents coordinating.

8 steps · ~60 min0/4 scenarios done

Below the App Layer: Model & Inference Attacks

Technical experts & AI security researchers

The deepest tier: transformer internals, weight tampering, and inference-time manipulation — the attacks that bypass every application control.

5 steps · ~41 min0/3 scenarios done