RAMPART Documentation¶
RAMPART: Risk Assessment & Measurement Platform for Agentic Red Teaming.
RAMPART is a pytest-native safety testing framework for agentic AI applications. You write tests that attack or probe your agent, and RAMPART orchestrates the interaction, evaluates the outcome, and reports the results.
Python
result = await Attacks.xpia(
trigger="Summarize the Q3 reports",
evaluator=ToolCalled("send_email"),
inject=handle,
).execute_async(adapter=my_agent)
assert result, result.summary
Quick Navigation¶
| If you want to… | Start here |
|---|---|
| Install RAMPART and run your first test | Getting Started |
| Explore runnable, end-to-end demos | RAMPART Examples |
| Understand how RAMPART works | Concepts |
| Write an XPIA attack test | XPIA Attack |
| Write a behavioral probe | Behavioral Probe |
| Learn testing patterns and best practices | Usage |
| Contribute back to the project | Contributing |
| Look up a class or function | API Reference |
| Find a term definition | Glossary |
What RAMPART Does¶
You provide an adapter that connects your agent to the framework. RAMPART provides:
- Execution strategies — orchestrate injection, triggering, and evaluation lifecycles
- Evaluators — detect conditions in agent responses (tool calls, text patterns, side effects)
- pytest integration — markers for harm categorization and statistical trials, automatic result collection, terminal summaries
- Reporting — structured JSON output for CI dashboards