Skip to main content

Each tutorial is a complete run: a target, a probe, and an evaluator. Start with the one that matches how your system is exposed.

Local LLM

Ollama on your machine. No provider API keys.

HTTP model

Any model behind a REST endpoint, via HttpTarget.

Basic red teaming

Built-in jailbreak and injection catalog with run_red_teaming().

LLM as judge

Score responses with another model instead of a heuristic.

Prompt dataset

Generate a dataset from a prompt, then evaluate it.

RAG

Generate questions from a knowledge base.

Multi-turn Crescendo

Escalate toward an objective across several conversation turns.

Compliance

Responsibility and safety evaluations on model outputs.

Persist results

Save and reload scenarios, test sets, and results.

Custom judge

CustomEvaluatorExpected or CustomEvaluatorObjective.