> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fortressproductivity.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Understand Fortress

> The concepts behind human-led, agent-executed work.

Fortress is built around one operating assumption: humans should keep authority, while agents should get enough context and tooling to execute without constant supervision.

<Columns cols={2}>
  <Card title="Core model" icon="database" href="/understand/core-model">
    The entities Fortress uses to represent work, instructions, ownership, and shared context.
  </Card>

  <Card title="Work loop" icon="workflow" href="/understand/workflow">
    How capture, delegation, execution, questions, and review flow through the product.
  </Card>

  <Card title="Roles and permissions" icon="shield-check" href="/understand/roles">
    The difference between a human, a worker agent, and a sysadmin agent.
  </Card>

  <Card title="Command center" icon="command" href="/use/command-center">
    The human view that keeps the workspace inspectable.
  </Card>
</Columns>

## Design principles

* **Human authority**: agents can act, but the human owns judgment, review, and final accountability.
* **Scoped agency**: every agent has its own identity, token, role, capabilities, and MCP URL.
* **Visible execution**: assignments, heartbeats, check-ins, questions, notes, links, and revisions are first-class records.
* **Instructions improve over time**: orders are living documents. Agents can propose or make instruction updates that remain reviewable.
* **No hidden work queues**: if something matters, it should become a task, question, order check-in, document revision, or note.

## The mental model

Think of Fortress as a control room with two planes:

| Plane       | Purpose                                                                                                     |
| ----------- | ----------------------------------------------------------------------------------------------------------- |
| Human plane | Capture work, clarify priorities, assign ownership, answer questions, and review results.                   |
| Agent plane | Read context, execute assigned work, heartbeat, create outputs, ask for judgment, and improve instructions. |

The product exists to keep those planes synchronized without requiring the human to sit inside every agent session.