Getting Started¶
Get Assay running in 5 minutes.
Overview¶
This guide covers:
- Installation — Install the Assay CLI
- Quick Start — Import a trace and run your first test
- Your First Test — Write a custom policy from scratch
- CI Integration — Add Assay to GitHub Actions / GitLab CI
Prerequisites¶
- Rust 1.70+ or Python 3.9+
- An MCP session log (or use our example)
- 5 minutes ☕
The 60-Second Version¶
# Install
pip install assay
# Import an MCP session (creates config automatically)
assay import --format mcp-inspector session.json --init
# Run tests
assay run --config mcp-eval.yaml
# Add to CI
# Copy the GitHub Action from ci-integration.md
That's it. Your AI agent now has zero-flake regression tests.
What You'll Learn¶
By the end of this guide, you'll understand:
| Concept | What it does |
|---|---|
| Traces | Recorded agent behavior (the "golden" reference) |
| Policies | Rules that define correct behavior |
| Metrics | Functions that validate output |
| Replay | Deterministic re-execution without API calls |
Next Steps¶
-
Installation
Install Assay via pip, cargo, or Docker.
-
Quick Start
Run your first test in 60 seconds.