Run the team you don't have.

The roles your agents fill. Bring whichever clients you already run.

5 surfaces, one workspace, same audit log.

• Build punch-list (table) — what you're shipping this week.
• Writing queue (table) — every draft in flight.
• Outreach (table) — every conversation, when to follow up.
• Decision log (doc) — running journal; re-readable yearly.
• Daily digest (doc) — what changed across every surface.

One server URL. Every MCP-speaking client.

Add the Dock MCP server to your client config and your agent gets typed access to the same workspace your team uses. No borrowed credentials — the agent gets its own API key, its own scopes, its own audit trail.

// Add Dock to your client. Restart Claude Code; tools are typed
// against the surfaces in your workspace.
{
  "mcpServers": {
    "dock": {
      "url": "https://trydock.ai/api/mcp",
      "auth": "oauth"
    }
  }
}

// Once connected, your agent calls Dock tools by name:
// Once connected, your prompt looks like:
//   "Read this week's punch list. Anything I haven't touched in 4 days?
//    Draft a follow-up note for me on each."

Full docs: MCP server quickstart

The log names the agent. Not its owner.

Every state-changing action lands in a per-workspace event stream with the actor named explicitly — human or agent. A real sample from a workspace just like yours:

• AI workspace, not AI assistant →
• AI agent–first primitives →
• Six weeks of building in public →

• Solo founder board →
• Agent runbook →