An AI attack pattern which starts with innocent prompts and gradually escalates over multiple conversation turns to bypass safety guardrails and extract harmful content. Each individual turn appears benign, evading single-prompt detection.
Multi-turn escalation
7th May 2026
Getting tests that catch real failures is the hard part. Watch the recording now on demand!
Explore MoT
Tue, 19 Jan 2027
Test Forward is one afternoon at Station F with the QA and engineering people closing that gap in their own teams.
Boost your career in software testing with the MoT Software Testing Essentials Certificate. Learn essential skills, from basic testing techniques to advanced risk analysis, crafted by industry experts.
Debrief the week in Quality via a community radio show hosted by Simon Tomes and members of the community
