# withHuman Overview

The approval layer for AI agents.

Agents can finally do real work. The bottleneck is what we let them do.

withHuman lets you decide which actions agents can take automatically, which they can’t, and which need a human’s approval first.

Connect your agents and manage their approval rules, reviewers, and decision history in one place.

Get started quickly with [hosted withHuman](https://app.withhuman.ai), or run the [open-source version](https://github.com/withHumanAI/withHuman) on your own infrastructure.

For those looking to learn withHuman at a deeper level, you should start with [concepts](/docs/concepts/how-withhuman-works), there's not much to learn, we promise.