CAT and AI agents

Mon, 19 Oct 2026 10:00:00 +0200

A coding agent writes code, runs a command, reads what came back and corrects itself. CAT fits that way of working without anything added to it, for three reasons.

Why CAT suits an agent #

The project is plain text in your repository. A CAT project is a .cat.yaml file: the data sources, the tests, the outputs. A test is a few lines of YAML with a query and an expectation. That is exactly the kind of file an agent writes well, and it goes through the same review and version control as the rest of your code.

Use CAT from a coding agent

Wed, 09 Sep 2026 10:00:00 +0200

The CAT skills are short procedures a coding agent loads when your request matches one of them: a data source to add, a test to write, results that must land in a pipeline, a failed test to explain. Each one is a SKILL.md that links the page of this documentation that owns every fact, so the agent reads the reference instead of remembering it. There are nineteen, one per situation, all named cat-<situation>, and they live in the public GitHub repository justcatit/cat-skills, one folder per skill, with a zip of the same folders on every CAT release.

AI agents on

CAT and AI agents

Why CAT suits an agent #

Use CAT from a coding agent