Free for 30 days on Scale.Start free
Write9 steps2-3 weeks (champion + legal sign-off is the bottleneck)

Write a customer case study from a real success

A 600-800 word case study with 2-3 verbatim quotes, 1-2 outcome numbers, customer logo / photo, and signed legal release. Live on your website, distributed to sales, ready for ads. The customer feels celebrated, not used.

Open in DockSee every step →

A 600-800 word case study with 2-3 verbatim quotes

A 600-800 word case study with 2-3 verbatim quotes, 1-2 outcome numbers, customer logo / photo, and signed legal release. Live on your website, distributed to sales, ready for ads. The customer feels celebrated, not used.

Spin up an agent for the heavy lifting

Drafts the case study from the interview transcript; tightens to 600-800 words; flags marketing fluff for cuts.

9 steps, 2 official links, 3 agent prompts

Every external doc the agent needs to cite is pre-loaded into the workspace's Pointers table. No hunting for the right URL mid-draft.

What's inside

Pre-loaded so day one is execution.

5Surfaces
9Steps
3Agent prompts
2Official links
5Tools mapped
Surfaces
  • tableDrafts
  • docCase study plan
  • tablePointers
  • tableDistribution
  • docStatus
See every step, link, and prompt
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>/write-a-customer-case-study and follow the agent prompt.”

Full MCP setup guideOther agent clients (Cursor, custom MCP)
FAQ

Common questions on this template.

How long should a case study be?
600-800 words for the long form, 200-300 words for the short form (used in sales decks + ads). Anything past 1000 words doesn't get read. Anything under 400 doesn't tell a story. The sweet spot fits on one page in print and reads in 2-3 minutes online.
How do I get the customer to talk for an hour?
Make it 30 minutes, not 60. Frame it as 'I want to capture your story in your words'. Offer a co-marketing benefit (their logo on your customer page, social shoutout, an introduction to a similar customer in your network). Customers who hit a real success metric usually want to talk about it — the friction is calendar time, not willingness.
Can my AI agents help write the case study?
Yes for drafting the long form from the transcript, tightening copy, flagging marketing fluff, designing the social cards. Not for the interview itself or the legal sign-off conversation. The agent reads the transcript and drafts; the human conducts the interview and manages the relationship.
How long does the whole process take?
Realistic: 2-3 weeks. Breakdown: 2-3 days to recruit the customer, 1 day for the interview + transcript, 1 day to draft, 5-7 days for champion review, 7-21 days for legal sign-off, 1-2 days to design + publish. Most of that is waiting on humans, not work. Run 2-3 case studies in parallel so the bottleneck of any one customer's legal team doesn't stall your output.
Related templates

More from Write

WriteMixed
Run a launch thread on X that converts

9-step plan for writing the launch thread, scheduling the engagement window, and converting impressions into signups, not just likes.

WriteMixed
Write a pre-seed pitch deck

10-step plan for the 10-12 slide pre-seed deck. Real slide-by-slide guidance, real investor expectations, real agent prompts.

WriteMixed
Write a product spec for a feature that ships

9-step plan for writing a feature spec that engineering can start on Monday with zero open questions and no surprise scope.

Browse all Write templates →
Used by these teams · 3

Teams that run this template, with their full setup.

Customer successUse case

Account continuity that survives CSM turnover.

Health, expansion potential, MRR: your account roster. QBR notes per account, a renewal queue that surfaces what's coming up. Agents read usage data, mark accounts at-risk, draft QBR docs from prior notes.

Open the use case
Agency operatorsUse case

Cross-client visibility without per-client tool sprawl.

Clients in a table, engagement context per client, a renewal queue. Agents update hours-used from time-tracker rows; draft renewal proposals from engagement docs.

Open the use case
Consultants & coachesUse case

Per-client narrative + reusable framework library.

Clients in a table, session notes per client, framework library as a doc. Agents draft session prep from prior notes; flag engagements ending in 30 days.

Open the use case

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.

Open in DockBrowse all templates →

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.