Glossary term
Jailbreak
A jailbreak is a prompt designed to get an AI model to bypass its safety rules and produce content it is meant to refuse. Testers collect known jailbreak patterns and run them automatically, alongside prompt injection tests, to check that guardrails still hold after model or prompt changes.
Read the full guide: Prompt Injection Testing: How QA Teams Test LLM Apps (2026)
More terms
Agentic testingAI hallucinationAI red teamingAnswer relevancyAPI testingBehaviour-driven development (BDD)CI quality gateContext precisionEnd-to-end testingExploratory testingFaithfulnessFlaky testGolden datasetIntegration testingLLM evaluationLLM guardrailsLLM-as-a-judgeLoad testingModel Context Protocol (MCP)OWASP Top 10 for LLM ApplicationsPage Object ModelPrompt injectionRegression testingRetrieval-augmented generation (RAG)SDETSelf-healing testsSmoke testingTest automationTest caseTest pyramidVisual regression testing
