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

# How OrgX Works

> A high-level overview of how OrgX turns goals into approved, verified work across MCP clients, Mission Control, and connected tools.

OrgX turns goals, decisions, artifacts, and tool context into a durable execution loop. You can start from Mission Control, an MCP client, ChatGPT where remote MCP is available, Cursor/Claude, or the OpenClaw plugin; agents then work through the IWMT hierarchy and stop at human approval checkpoints before important writes.

## Questions This Page Answers

* What happens from task intake to shipped artifact?
* Which agent domains are used in routing?
* Where does human approval fit?
* Why this architecture is safer than autonomous black-box execution?
* Which integrations are live today vs planned?

## The Big Picture

```mermaid theme={"dark"}
flowchart LR
    subgraph You
        A[Mission Control]
        B[ChatGPT / MCP clients]
        C[Cursor/Claude]
        CC[OpenClaw Plugin]
    end

    subgraph OrgX
        D[Agent Orchestrator]
        E[Decision Queue]
        F[Artifact Storage]
        FL[Intelligence Flywheel]
    end

    subgraph Your Tools
        G[Linear]
        H[GitHub]
        I[Planned connectors]
    end

    A --> D
    B --> D
    C --> D
    CC --> D
    D --> E
    D --> F
    D --> FL
    FL --> D
    D <--> G
    D <--> H
    D -. planned .- I
    E --> A
    E --> B
```

## How Agents Work

<Steps>
  <Step title="Task Enters the System">
    A task arrives from a connected tool, you create an initiative, or you ask an
    agent to do something via Mission Control, ChatGPT with remote MCP enabled,
    Cursor, Claude, or the OpenClaw plugin.
  </Step>

  {' '}

  <Step title="Agent Selection">
    OrgX analyzes the task and selects the best agent(s)--Engineering, Product,
    Marketing, Sales, Design, or Operations--with the Orchestrator coordinating
    cross-domain dependencies.
  </Step>

  {' '}

  <Step title="Agent Executes">
    The selected agent works on the task, reading from your connected tools and
    generating artifacts (specs, PRs, campaigns, reports).
  </Step>

  {' '}

  <Step title="Decision Checkpoint">
    Before shipping anything, the agent surfaces a **decision** for your approval
    with full context and reasoning.
  </Step>

  {' '}

  <Step title="You Approve">
    You review the decision in Mission Control, an MCP client, ChatGPT where
    remote MCP is enabled, Cursor, or OpenClaw. Approve to ship, reject with
    feedback, or edit before approving.
  </Step>

  <Step title="Artifact Ships">
    Approved work becomes a verified artifact—a PR gets opened, a campaign gets
    scheduled, a spec gets published.
  </Step>
</Steps>

***

## Access Surfaces

OrgX works wherever you work:

<CardGroup cols={2}>
  <Card title="Mission Control" icon="compass">
    Full web dashboard with Next Up scored queue, Slices Plane IWMT hierarchy
    view, live agent dashboard, and red-dot control plane for proactive health
    monitoring.
  </Card>

  <Card title="OpenClaw Plugin" icon="plug">
    Browser-native OrgX dashboard with 60-second pairing, automatic MCP config,
    and live decision triage. [Set up OpenClaw](/docs/guides/openclaw-plugin-setup)
  </Card>

  <Card title="ChatGPT / Remote MCP" icon="comments">
    Conversational interface for approvals, bulk decisions, and organizational memory
    queries in accounts and workspaces where custom remote MCP connectors are
    available.
  </Card>

  <Card title="Cursor/Claude" icon="code">
    IDE integration via MCP for developer workflows and agent-assisted coding.
  </Card>
</CardGroup>

***

## Integration Flow

When you connect a tool like Linear or GitHub, here's what happens:

```mermaid theme={"dark"}
sequenceDiagram
    participant You
    participant OrgX
    participant Tool

    You->>OrgX: Connect Linear
    OrgX->>Tool: OAuth authorization
    Tool->>OrgX: Access granted
    OrgX->>Tool: Sync projects & issues
    Tool->>OrgX: Webhook for updates
    Note over OrgX: Agents can now read/write
```

### What Gets Synced

| Tool   | OrgX Reads                       | OrgX Writes                         |
| ------ | -------------------------------- | ----------------------------------- |
| Linear | Projects, issues, labels, states | Comments, new issues, state changes |
| GitHub | Repos, branches, PRs             | New PRs, comments                   |
| Slack  | Planned                          | Planned notifications and approvals |

***

## Data & Privacy

<AccordionGroup>
  <Accordion title="Where is my data stored?">
    OrgX stores your organizational data (initiatives, decisions, artifacts) in
    a secure, encrypted database. Integration tokens are stored with
    column-level encryption.
  </Accordion>

  {' '}

  <Accordion title="What do agents have access to?">
    Agents only access tools you've explicitly connected via OAuth. Each
    integration requests specific scopes--you can see exactly what's being
    requested during setup.
  </Accordion>

  <Accordion title="Can I disconnect a tool?">
    Yes, anytime via Settings → Integrations. This immediately revokes OrgX's
    access.
  </Accordion>
</AccordionGroup>

***

## Real-Time Updates

OrgX keeps you informed as agents work:

* **Progress streams**: See agents thinking and working in real-time
* **Decision notifications**: Get alerted when agents need your input
* **Sync status**: Know when integrations are connected and healthy

<Info>
  Current production connectors center on Linear, GitHub beta, Stripe billing,
  and MCP/OpenClaw access surfaces. Slack, Notion, HubSpot, Figma, and Mailchimp
  are roadmap items or selected-runtime stubs, not generally available native
  integrations.
</Info>

***

## Key Concepts

### IWMT Hierarchy

OrgX organizes work using the **IWMT hierarchy** — Initiative, Workstream, Milestone, Task. This structure enables automatic cascade execution:

| Level          | What It Is                                              |
| -------------- | ------------------------------------------------------- |
| **Initiative** | A high-level goal (e.g., "Q1 Product Launch")           |
| **Workstream** | A parallel execution track within an initiative         |
| **Milestone**  | A checkpoint or deadline within the initiative timeline |
| **Task**       | An individual unit of work assigned to an agent         |

When a task completes, the next queued task in the workstream auto-starts. When all tasks in a milestone complete, the milestone auto-closes. Cross-workstream dependencies resolve automatically through DAG resolution.

### Core Entities

| Concept      | What It Is                                                                                         |
| ------------ | -------------------------------------------------------------------------------------------------- |
| **Agent**    | A specialized AI worker (Engineering, Product, Marketing, Sales, Design, Operations, Orchestrator) |
| **Decision** | A checkpoint where agents need your approval                                                       |
| **Artifact** | A verified output (spec, PR, campaign, report)                                                     |

### Intelligence Flywheel

The flywheel connects agent execution to measurable outcomes, building trust over time:

* **Value Ledger**: Every action generates a receipt tracking cost and attributed value
* **Trust Levels**: Agents earn trust per capability (`read_only` → `draft` → `act_with_approval` → `autonomous`)
* **Autonomous Sessions**: Budget-bounded overnight execution with morning brief review
* **Org Learnings**: Agents share discoveries across the org for continuous improvement

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Agents" icon="robot" href="/docs/platform/agents">
    Learn about each agent type and their capabilities.
  </Card>

  <Card title="Decisions" icon="check-circle" href="/docs/platform/decisions">
    Understand the approval workflow.
  </Card>
</CardGroup>