Prompt Engineering & LLMIntermediateTier 2 · $99
Red-Teaming AI
Probing a model for harm, documenting reproduction steps and rating severity.
3 modules150 minutes of material10 exam questions · 80% to pass
Syllabus
01Harm taxonomy
50 min- Map a finding to the right harm category
- Separate capability from intent
02Attack surface
55 min- Enumerate the ways a product can be driven to harm
- Write reproduction steps
03Severity and containment
45 min- Rate severity consistently
- Respect the containment boundary
Assessed concepts
The exam tests these directly. Definitions are summarised here; the exact answer key stays on the server.
Harm taxonomy
Attack surface
Severity rating
Reproduction steps
Containment boundary