Promptfoo

What it does

Promptfoo is a local-first CLI and Node.js library for testing LLM applications from configuration files. It combines quality evaluation, provider comparison, CI gates, and adversarial red teaming without requiring teams to move their test suite into a hosted platform.

• Matrix comparisons across prompts, test cases, and model providers
• Deterministic, model-graded, RAG, conversational, and agent-trajectory assertions
• Automated red teaming, caching, concurrency, reports, and CI/CD integration

Where it fits

Declarative regression tests and side-by-side comparisons of prompts, models, RAG systems, and agent configurations, especially when red teaming is also required.

Use it after defining the behavior that matters, collecting representative cases, and deciding how each case will be graded. A tool can execute and organize an eval, but it cannot decide which failures are costly for your users.

Limitations and cautions

• Model-graded checks inherit the judge model's variance, bias, latency, and cost.
• Local execution does not keep data local when a configured remote model provider receives prompts and outputs.

How to evaluate the evaluator

Before using any score as a release gate, create a small evaluator-validation set that humans have labeled. Compare false passes, false failures, disagreement by failure type, run-to-run variance, latency, and cost. Keep deterministic checks for verifiable facts, calibrate model judges against domain experts, and review raw traces when aggregate scores move.