Red-Teaming AI Certification
Probing a model for harm, documenting reproduction steps and rating severity.
What this certification covers
Red-Teaming AI sits in the Prompt Engineering & LLM track (Intermediate). You read 3 written modules in order — each one has to be completed before the next opens — then sit a ten-question exam marked on our servers against a fixed answer key. Pass at 80% and the certificate is issued.
01Harm taxonomy50 min
- Map a finding to the right harm category
- Separate capability from intent
02Attack surface55 min
- Enumerate the ways a product can be driven to harm
- Write reproduction steps
03Severity and containment45 min
- Rate severity consistently
- Respect the containment boundary
Concepts tested
Harm taxonomy
The fixed category list a finding must be filed under.
Attack surface
Every path by which a user can push the product toward harm.
Severity rating
A consistent scale from nuisance to real-world danger.
Reproduction steps
The minimal prompt sequence that reliably triggers the finding.
Containment boundary
The limit past which a test stops being safe to run.
How to get certified
- 1. Create a free account — no card, no payment at signup.
- 2. Read the 3 modules in order and mark each complete.
- 3. Sit the ten-question exam. Retakes are free.
- 4. If you pass, pay $99 once to unlock the signed certificate.