# CTRLRun

> CTRLRun stops AI agents from taking wrong, restricted, or malicious actions in your workflows. Every action is checked against your rules before it runs.

## Docs

- [The execution safety layer for AI agents](https://ctrlrun-tests-t483-t486.mintlify.site/docs.md): The last check before an AI agent does something it can't undo. Autonomy belongs to the action, not the agent.
- [Run it in production](https://ctrlrun-tests-t483-t486.mintlify.site/docs/production/index.md): SQLite is the default and is production-grade on one host. Postgres is for many hosts. What survives a crash, and what you do yourself.
- [banner](https://ctrlrun-tests-t483-t486.mintlify.site/docs/reference/api/banner.md): Log SPEC-v0.3 §6.5's observe banner, once per `Control`. An adapter MUST call it (§3.6).
- [needs_approval](https://ctrlrun-tests-t483-t486.mintlify.site/docs/reference/api/needs_approval.md): Does this call need a human? For a framework that asks before it invokes (SPEC-v0.5 §3.5).