Build

Agent runbook & audit cycle

Living runbook for your agent fleet, audited weekly. Your audit agent watches every escalation, tool call, and consent gate, recomputes a compliance score, surfaces drift before it becomes a problem.

Open in Dock

Runbook

Allowed tools

Audit log

Compliance score

+1 more

TitleStatusOwner

Living runbook for your agent fleet, audited weeklyactiveAgent

Runbook (doc)queuedYou

Allowed tools (table)draftedAgent

Audit log (table)draftedYou

…

Public preview of the cloned workspace. Same chrome you'll see after Open in Dock.

Living runbook for your agent fleet

Living runbook for your agent fleet, audited weekly. Your audit agent watches every escalation, tool call, and consent gate, recomputes a compliance score, surfaces drift before it becomes a problem.

Spin up an agent for the heavy lifting

Audit agent (yours): watches the Audit log surface. Runs a weekly compliance pass on Sunday — recomputes the score doc, names the top 3 drift patterns, drafts runbook updates when actual behavior diverges from what the runbook says.

5 surfaces, one workspace

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

What's inside

Pre-loaded so day one is execution.

5Surfaces

Surfaces

docRunbook
tableAllowed tools
tableAudit log
docCompliance score
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.

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.
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.
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>/agent-runbook and follow the agent prompt.”

Full MCP setup guide Other agent clients (Cursor, custom MCP)

FAQ

Common questions on this template.

What is the agent runbook template for?

Living documentation for your agent fleet that gets audited weekly instead of rotting. Your audit agent watches every escalation, tool call, and consent-gate event in the Audit log surface and recomputes a Compliance score each Sunday. Catches drift early, keeps the runbook in sync with actual fleet behavior.

Who should use this template?

Anyone running 2+ agents in production where consistency matters. Particularly useful for teams where agents have access to dangerous tools (billing, sending email, modifying production data) and need a clear paper trail of what was called when.

How do my agents drive this?

Two agents share the workspace. Your operator agent writes events to Audit log as they happen — wired via the workspace's webhook API on row.create. Your audit agent reads Audit log every Sunday, recomputes Compliance score, and drafts runbook updates. Connect both at trydock.ai/agent-invites and seed them with the agentPrompt.

Related templates

More from Build

BuildMixed

Launch your iPhone app on the App Store

10-step plan from 'I have a build on my Mac' to 'users are downloading from search.' Real Apple gates, real gotchas, real agent prompts.

BuildMixed

Build a webapp in a day

10-step plan from blank idea to deployed app with auth, a database, and a domain — all in 24 hours. Battle-tested defaults so you don't waste 6 hours picking a stack.

BuildMixed

Launch your Android app on Google Play

10-step plan from 'I have an APK on my laptop' to 'users are installing from Play search.' Real Google gates, real gotchas, real agent prompts.

Browse all Build templates →

Used by these teams · 3

Teams that run this template, with their full setup.

EngineeringUse case

Ship more code. Run agents on the build.

Sprint backlog, spec docs, deploy logs: one workspace. Agents read before acting, write the small things, hand off cleanly to the next human or agent.

Open the use case

OperationsUse case

Runbooks that get tested + run.

Vendor management, runbook library, incident-style ops drills. Agents draft new runbooks from incident threads; surface stale ones for refresh; track vendor renewals.

Open the use case

Solo buildersUse case