Install promptfoo, configure providers and write your first test suite in YAML

Master built-in assertions, custom scorers, and threshold-based pass/fail logic

Automated adversarial testing — scan for jailbreaks, PII leaks and prompt injections

Gate deployments with LLM quality checks in GitHub Actions, pass-rate thresholds and diff reports

Install LangTest, configure the Harness, and connect HuggingFace or OpenAI models

Test model stability under typos, case changes, contractions and entity swaps

Detect demographic, gender, religion and nationality biases in NLP model predictions

Write custom test types, set per-category thresholds, and export shareable HTML reports

Install DeepEval, write your first test case, and run built-in metrics like answer relevancy and hallucination

Evaluate RAG pipelines with faithfulness, context recall, context precision and answer relevancy

Build domain-specific metrics with G-Eval and write fully custom scorer classes

Install RAGAS, build a Dataset, and compute faithfulness, answer relevancy and context metrics

Auto-generate evaluation testsets from your documents and write custom RAGAS metrics

Track RAG quality in production with continuous RAGAS scoring and drift detection

Instrument LangChain apps with LangSmith tracing — capture runs, inspect spans and debug failures

Create evaluation datasets, run automated evaluators and track quality metrics over time