Real AI agent use cases, with sources and setup prompts

Deploy an open-source team agent in Slack with your own models

QM, open-sourced by Y Combinator, gives every employee their own agent with memory, files, permissions and a sandbox, and also works in Slack channels: it searches notes, email and docs, triages inboxes, opens PRs and runs scheduled jobs. You deploy it by telling your coding agent to follow the repo guide.

$17/mo1 dayAdvancedSource linked

Source

@RoundtableSpace on X · 2026-10-20

Written in our own words. Credit to the original author. Link checked 2026-10-21.

What they did

QM, open-sourced by Y Combinator, gives every employee their own agent with memory, files, permissions and a sandbox, and also works in Slack channels: it searches notes, email and docs, triages inboxes, opens PRs and runs scheduled jobs. You deploy it by telling your coding agent to follow the repo guide.

Result (as claimed)

15.5k GitHub stars; MIT licensed, runs in your own cloud.

Tools they used

Claude CodeSlack

Cost: Claude Code: from $17/mo.

Set it up

  1. Map the task

    Write the trigger, the inputs, the decisions and the output. Note which steps need a human yes.

  2. Connect the tools

    Set up Claude Code, Slack with the narrowest permissions that work. Use a test account or sandbox first.

  3. Build the workflow

    Create the steps in order. Add an approval step before anything sends, pays or deletes.

  4. Run it on real but low-stakes data

    Run a few times, read every output, and fix prompts or rules that misfire.

  5. Schedule and monitor

    Turn on the schedule or trigger, and add a daily summary or alert so you notice failures.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Deploy an open-source team agent in Slack with your own models
What the original author did: QM, open-sourced by Y Combinator, gives every employee their own agent with memory, files, permissions and a sandbox, and also works in Slack channels: it searches notes, email and docs, triages inboxes, opens PRs and runs scheduled jobs. You deploy it by telling your coding agent to follow the repo guide.
Reported result (as claimed by the author): 15.5k GitHub stars; MIT licensed, runs in your own cloud.
Source: https://x.com/RoundtableSpace/status/2112465092105121872
Tools they used: Claude Code, Slack
Category: Automation & business

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5

Get five new use cases tomorrow morning

Free. Real sources. Unsubscribe any time.

Guides for this use case

How to automate email and your inbox with AI agents · How to build agent memory and context layers · How to add memory to coding agents · How to vibe code an app with Claude Code

Related use cases