Skip to main content

TrustTest is agnostic to the model under test. Connect a target, then attach probes and evaluators. The web UI currently requires an LLM that exposes a REST API.

HTTP

HttpTarget for any chat or completion endpoint, including multi-turn probes.

LLM providers

OpenAI, Azure, Anthropic, Google, Groq, Ollama, vLLM, and generic HTTP judges.

Custom target

Implement the target interface when the system is not HTTP.

Results client

Write JSON locally, or persist the same artifacts in NeuralTrust.
Run TrustTest in a separate process from the model. In-process evaluation couples failures and makes multi-turn probes harder to reproduce.