# Scrutineer

> Kubernetes-native governance for autonomous AI agents — policy, approvals, and an audit trail the agent can't forge.

Every documentation page is also published as raw Markdown: drop the
URL's trailing slash and append `.md` (for example
http://scrutineer.sh/docs/getting-started/quickstart.md).
Source, issues, and design docs: https://github.com/grantbarry29/scrutineer

## Docs


### Getting Started
- [Quickstart](http://scrutineer.sh/docs/getting-started/quickstart.md): One command to a running, lock-verified Scrutineer on a local kind cluster — about five minutes.
- [Demo: untamperable egress governance](http://scrutineer.sh/docs/getting-started/demo.md): Two sessions, same bring-your-own agent: a live denial, a bypass attempt killed by the routing lock, and evidence the agent couldn’t forge.
- [Install on your cluster, step by step](http://scrutineer.sh/docs/getting-started/install.md): Every command visible, on your existing cluster: install, deny one domain, run an agent, read the proof.


### Concepts
- [Core concepts](http://scrutineer.sh/docs/concepts/core-concepts.md): Sessions, policies, profiles, the two locks, and evidence assurance.


### Reference
- [FAQ](http://scrutineer.sh/docs/faq.md): Why not just a firewall, a service mesh, or a CNI? Honest comparisons and the reasoning behind the enforcement model.

## Agent resources

- [Sitemap](http://scrutineer.sh/sitemap.xml)
- [RSS (full text)](http://scrutineer.sh/index.xml)