Announcements, hands-on expertise and honest comparisons from the team building EvaliQA. One problem per post, from the work we do with clients.
7 posts tagged Red teaming. Clear filters
Promptfoo is a free open-source CLI for testing prompts and red teaming from a config file. We compare it with EvaliQA on test cases, judges, multi-turn runs, red teaming, production monitoring and reporting, and say where each one is the right pick.
Read the postA 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 postEvery new EvaliQA workspace now opens with the ShopWave demo project, a real support bot with planted weak spots, two test plans and two finished runs. Read the judge's reasoning on a failed row before you connect your own system.
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 postDeepEval is a free Python library that scores test cases from a test file. EvaliQA is a hosted workspace where the whole team edits the test bank, compares runs, red-teams and scores production traffic with the same metrics.
Read the post
