> For the complete documentation index, see [llms.txt](https://cerebral-systems.gitbook.io/cerebral-systems-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cerebral-systems.gitbook.io/cerebral-systems-docs/getting-started-1.md).

# Getting Started

Warrant is the security boundary between an agent's intent and its side effects. An agent proposes a bounded action; Warrant checks it against policy, holds it for human approval when the risk warrants, executes it through a registered actuator, and records tamper-evident audit evidence.

Start here:

* **Quickstart** — go from signup to a policy-gated, approved, audited action in about five minutes, against the hosted sandbox.
* **Authentication & API keys** — the key scopes (agent, approver, admin), how to send them, and how to rotate them.
* **Agent integration** — wire Warrant into your agent so every mutating tool resolves to one proposal, and only allowed actions run.

The rule that makes it a boundary: an agent must never receive `allow` and then call the provider itself. Warrant owns execution.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://cerebral-systems.gitbook.io/cerebral-systems-docs/getting-started-1.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.