How we evaluate AI systems, and what the metrics actually measure.
4 posts in Expertise tagged Red teaming. Clear filters
A spreadsheet of public jailbreak prompts tells you whether your AI system refuses those strings, not whether an attacker can get what they came for. How to red-team from attack objectives instead, and how EvaliQA turns them into a breach rate per vulnerability and technique.
Read the postPrompt injection sits at the top of the OWASP Top 10 for LLM applications, and most teams test only the direct form. Here is how to test direct attacks, payloads hidden in retrieved data and multi-turn build-ups in EvaliQA, and what breach rate to accept before you ship.
Read the postAgents fail across turns in ways no single-turn check can see: they repeat a tool call, lose what the user said, and drift out of their role under pressure. This guide shows how to catch all three in EvaliQA, offline with multi-turn scenarios and live with online evaluation.
Read the postTwenty clever prompts in a spreadsheet is not a red team. What separates an exercise you can repeat from an afternoon of anecdotes.
Read the post
