Jailbreak Resistance Certification
Testing instruction hierarchies and refusal calibration against multi-turn pressure.
What this certification covers
Jailbreak Resistance sits in the Prompt Engineering & LLM track (Expert). 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.
01Instruction hierarchy55 min
- Rank system, developer and user instructions
- Spot hierarchy collapse
02Escalation patterns55 min
- Recognise role-play and pretext escalation
- Test encoded payloads
03Refusal calibration45 min
- Refuse the harmful part, keep the useful part
- Measure false refusals
Concepts tested
Role-play escalation
A harmless persona used to walk the model toward a prohibited answer.
Instruction hierarchy
The fixed precedence between system, developer and user instructions.
Refusal calibration
Refusing narrowly enough to keep the legitimate request answerable.
Multi-turn drift
A policy eroding across turns where no single turn is a violation.
Escape encoding
Payloads hidden in base64, translation or homoglyphs to dodge filters.
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.