> For the complete documentation index, see [llms.txt](https://docs.brava.finance/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.brava.finance/platform/agents-and-mandates.md).

# Agents and Mandates

Draft: how agents propose within defined mandates.

## Agents and mandates

> **Draft. Do not publish as-is.**
>
> This page needs a product owner to confirm the mandate model and AI connection flow.

The agent proposes. The mandate defines what is possible. You decide what moves.

### Agents

An agent is an AI acting through Brava on your behalf. It researches opportunities, assesses risk, and prepares transactions.

It does not sign. It does not hold a workspace role. Its work appears as a **pending agent action** on the Portfolio screen and waits.

A plan is not an action. Nothing moves until you approve and your custodian signs.

### Mandates

A mandate is the boundary an agent works inside. It defines what the agent may propose and how far.

{% hint style="warning" %}
Confirm who defines a mandate, its constraints, its scope, and how outstanding proposals behave when it changes.
{% endhint %}

### Connecting your AI

MCP connection guidance needs its own reviewed workflow. It should define what an agent can read, prepare, and never execute.

### Why it is built this way

Research and execution are different acts. The boundary between them is where control sits.

An agent can be fast and wrong. A mandate limits its proposals. Your approval and signature make the decision yours.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.brava.finance/platform/agents-and-mandates.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
