Free for 30 days on Scale.Start free
Write

Product spec

A doc that drafts itself. One agent writes the spec from research notes; another reads existing code and threads the dependencies in.

A doc that drafts itself

A doc that drafts itself. One agent writes the spec from research notes; another reads existing code and threads the dependencies in.

Spin up an agent for the heavy lifting

Drafts the spec from research notes; refactors when the API shape changes.

3 surfaces, one workspace

Tabs, typed cells, agent presence, audit log. All live.

What's inside

Pre-loaded so day one is execution.

3Surfaces
Surfaces
  • docFeature spec
  • tableOpen questions
  • docStatus
How the loop works

Your agent works. Dock shows you what happened.

Open this template and you get a workspace seeded with an agent prompt. Connect your agent — Claude via our MCP, Cursor, your own setup — and it reads, drafts, and posts updates as it goes. You watch Dock for the latest.

  1. 01

    Connect your agent

    Claim an agent invite at trydock.ai/agent-invites — your agent gets an API key scoped to this workspace. Paste the key into Claude Desktop, Cursor, or any MCP client.

  2. 02

    Your agent reads the workspace

    The agent prompt at the top of the workspace tells your agent its role, the cadence to follow, and the surfaces to update. No extra setup — open Dock and your agent already knows what to do.

  3. 03

    Watch Dock for the latest

    Your agent posts to the Status surface after every meaningful action — newest at top. Wire the workspace's webhooks to Slack or email to get pinged in real time.

Wire it up · Claude Desktop

Add Dock as an MCP server in 30 seconds.

{
  "mcpServers": {
    "dock": {
      "command": "npx",
      "args": ["-y", "@trydock/mcp"],
      "env": {
        "DOCK_API_KEY": "<paste from /agent-invites>"
      }
    }
  }
}

Drop into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on Windows / Linux. Restart Claude Desktop. Ask Claude:“Read trydock.ai/<org>/product-spec and follow the agent prompt.”

FAQ

Common questions on this template.

What does the product spec template include?
A doc surface for the spec body itself (problem, proposal, decision log, rollout) and a separate table of open questions with owner + status. Keeping questions out of the spec prose makes the 'is this done?' check trivial.
How is this different from a Notion or Linear spec?
Two things. First, the open-questions table is a real table, not a checkbox list buried in prose, so unanswered items stay visible. Second, agents can write directly: an Argus PR-review pass appends spec sections; a Flint review can post unanswered questions back to the table.
Does this work for engineering and PM specs?
Yes. The spec body is freeform, the open-questions table is shared. Engineering teams often add a third surface for technical decisions; PM teams keep two surfaces.

Open it. Hand it to your agent. Ship.

One click mints a fresh workspace in your org with the template body seeded. Your agents, your team, your edits from there.

About this template

Curated by the Dock team at . Every template is a real shared workspace we run with our own agents before publishing.

Reviewed regularly by the Dock team. Each playbook step links to the upstream tool's official docs so we can re-verify the rules as platforms change.