← Back to library

Get alerted when a team food order opens in Slack

matt palmer (@mattyp) says group DoorDash orders come up often on the Cursor team, scattered across channels, and joining them was confusing. His bot watches Slack for group-order links and alerts him when one appears. He can ask it to explore a menu he likes; it suggests options and links him straight to where he adds his food.

  • OutcomeHave a bot watch Slack for group delivery orders, alert you when one opens, suggest dishes and link you to join.
  • SetupMinutes
  • LevelStarter
  • Creditmatt palmer (@mattyp)
View original
Works with
Grok Bot

Published Oct 23, 2026Updated Oct 23, 2026AI dry run on sample input: passed Oct 23, 2026Source verified Oct 23, 2026

When should you use it?

  • Your team runs group food orders in Slack
  • You often miss the cutoff
  • Menus slow you down

Not for: Ordering on someone else's account; Teams that ban bots in channels

What do you need, and what do you get?

You need

  • Slack access
  • Group order link pattern
  • Food preferences

You get

  • Alert when an order opens
  • Menu suggestions
  • Direct join link

How does it work, step by step?

  1. Find the patternNote what group-order links look like in your channels.
  2. Watch channelsHave the bot watch those channels for the link.
  3. Alert youSend a direct message with the restaurant and cutoff.
  4. SuggestOffer a few dishes based on your preferences.
  5. You addOpen the link and add your own items.

The prompt

Our own prompt, inspired by matt palmer (@mattyp) and written to work in Grok Bot. Values in lime are placeholders.

Fill in the blanks (optional; the copied prompt uses your values)

Prompt3 variables
Watch {slack_channels} for group-order links from {delivery_service}. When one appears, DM me the restaurant, who started it and the cutoff time.
Suggest three dishes from that menu based on {my_preferences}, with the join link. Do not add items or pay.

Inspired by matt palmer (@mattyp): Intro to Grok Bot. The prompt above is written by playbooks.bot in our own words; nothing from the original is quoted.

What can go wrong?

  • Bots reading many channels can surface private messages; scope access.
  • Cutoff times vary; include them in the alert.
  • Let you, not the bot, add to the shared order.

Our take

A small, low-risk watcher is a good first bot for a team. It reads, alerts and suggests, and you still take the one action that touches a shared order. Scope it to the channels where orders actually appear, include the cutoff time in every alert, and keep your preferences in a short note so suggestions improve. Prefer alerting over auto-joining, since adding the wrong items or missing a dietary need is embarrassing. The same pattern works for any recurring team signal buried in Slack noise: standups, on-call pages or document reviews. Ask teammates before connecting a bot that reads channels, and limit it to the minimum channels needed. Do not give it permission to post in those channels unless you want it announcing itself to the team. Review the first week of alerts to tune keywords and cut false positives from people mentioning the delivery service in other contexts. Share the pattern with teammates who struggle with the same noise.

Where the time goes back: You stop missing team orders and spend less time on the menu.

FAQ

Why bother?
He found the orders overwhelming and was easily distracted by menu choices.
Does it order for him?
It gives options and links him to the right place to add food.

Source and credit

Inspired by matt palmer (@mattyp). We describe the idea in our own words, link to the original, and wrote the prompt ourselves; nothing is quoted.

Inspired by
Intro to Grok Bot
Creator
matt palmer (@mattyp)
Published on
X
Original date
Aug 11, 2026
License
Not openly licensed (the poster keeps all rights), so we quote nothing and link to the original
Originally for
Grok Bot
AI dry run
Oct 23, 2026: passed. Dry-run tested by our AI test agent on sample input. PASS: Gates held on desk check; no live sends, bookings or purchases.
AI dry run on sample data; not run with live connected accounts. The playbooks.bot test agent filled the prompt with synthetic inputs, produced the output and checked it against the page's stated outputs and guardrails.
Verified
Oct 23, 2026: source link resolves to the original, the credited creator published it, our excerpt or prompt matches it, and the license allows our use.

Are you the creator? Claim or correct this page.

More in Operations & Admin

All 203 Operations & Admin playbooks →

Related playbooks

Operations & AdminPrompt✓ AI dry run

Aim the agent at a janky internal app after it maps the UI

Have the agent study a janky internal UI out loud, complete one end-to-end task with a recording, and stop for login walls instead of guessing credentials.

Credit: Carnage (@0xCarnagee)

Under an hour
Operations & AdminPrompt✓ AI dry run

Audit how you manage your agent team, not only the agents

Have your chief-of-staff agent review the last 30 days of how you delegated, clarified, interrupted, corrected, assigned, approved and followed up across your agent team, score eight management areas with evidence, list your three biggest weaknesses, and draft a seven-day improvement plan, without changing any bot, routine or instructions until you approve.

Credit: Michael Fenech (@Michael_Fenech_)

Under an hour
Operations & AdminPrompt✓ AI dry run

Audit how your agents pick tools before buying more usage

Have your lead agent review the recurring jobs it can see, note which apps, scripts, browser sessions or full computer control each one relies on, flag jobs that take a heavier route than needed or rely on remembered facts, check permissions and fallbacks, and then propose three side-by-side experiments before anything is changed.

Credit: Michael Fenech (@Michael_Fenech_)

Under an hour
Operations & AdminPrompt✓ AI dry run

Find the old instructions your agent keeps obeying

When you keep correcting an agent about the same thing, trace the correction to the conflicting instructions behind it, fix the source with your approval, and retest safely.

Credit: Michael Fenech (@Michael_Fenech_)

Minutes