For the complete documentation index, see llms.txt. This page is also available as Markdown.

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 Do not publish as-is.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.

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.

Last updated