Show HN: CATT 0.2.1: Test agents/services against a Muse/Instinct-alike, in CI
The Consumer Agent Testing Tool (CATT) 0.2.1 has been released to help developers test AI agents against surrogate emulation targets like Muse and Instinct. It allows for scripted or model-driven testing of MCP servers and HTTP APIs to ensure consistent agent behavior across builds.
Why it matters
As AI agents become more integrated into business workflows, standardized testing frameworks are essential for ensuring reliability and security in automated decision-making.
Consumer Agent Testing Tool (CATT) tests how an assistant uses your service. Run a scripted or model-driven agent against an MCP server, an MCP app, a website or an HTTP API. Check what the service did, inspect the evidence, and compare results across builds.
Muse and Instinct are supported surrogate emulation targets. Muse remains the default. Both use the shared connector testing contract , including routing, memory, payments, browser/HTTP tasks and scheduling. See the Instinct research for its sources and limits. The model that drives a trial is separate from the assistant being emulated.
Contributing | Security | Changelog | MIT license
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in