Get started

How we keep the office stocked

People request snacks through a Slack shortcut, and an agent batches the requests weekly, prepares an order, and posts it for the office manager to approve before placing anything.

×
Slack
Written by
The OpenChatly Team
Published
January 28, 2026
Reading time
6 min read
Topics
Operations, Case Study, Fun

Keeping an office stocked is a small recurring chore that never quite has an owner. Requests come in over Slack, hallway conversations, and sticky notes; the office manager reconciles them into an order; and half the time a request is forgotten by the time the order goes in. It's low-stakes, but it's steady work.

We handle it with an agent on Kortix. People request snacks through a Slack shortcut, and once a week the agent batches every request, prepares an order, and posts it for the office manager to approve. Nothing is placed until a person signs off.

Team
Kortix
Control surface
Slack
Connected systems
Slack · Ordering account
Mode
Weekly batch · human-gated

The problem

Snack requests arrive one at a time and out of band. Someone asks in a channel, someone else mentions it in passing, and the office manager is left assembling a list from memory. Requests get dropped, duplicates slip through, and the order goes in later than it should.

The task is simple but constant. It needs one place to collect requests, a way to batch them on a schedule, and a person's sign-off before any money is spent — none of which a shared spreadsheet or a recurring calendar reminder actually provides.

What we built

Requests come in through a Slack shortcut, so there's one place to submit them. Once a week a cron trigger spawns an isolated session that collects the week's requests, prepares an order against the ordering account, and posts the draft in Slack for the office manager to approve. Only after approval does it place anything.

How it works

1

Copy the setup prompt into a new session

Open your Kortix workspace, start a new session, paste this prompt and send it. The agent writes the agent file, the snack batching skill and the weekly trigger, and opens a change request for you to review. Prefer clicks? Choose Use this template instead.

Setup prompt

Set up a weekly office snacks agent in this workspace.

  1. Create the agent agents/office-snacks.md. Its job is to batch the week's snack requests into one draft order for the office manager to approve. It may read and post in #office through Slack, and it uses the ORDERING_ACCOUNT_API_KEY secret for the ordering account.

  2. Create the skill skills/snack-batching/SKILL.md with these rules:

    • The cutoff is your last posted draft order in #office, or the last 7 days if there is none. Collect every snack-shortcut request since then.
    • Merge duplicate and near-duplicate items into one line, add up the quantities and list every requester.
    • Always add the standing staples: coffee beans, sparkling water and oat milk.
    • Build the cart on Amazon within $150. When it runs over, trim the non-staple items with the fewest requesters first. Never check out.
    • Post the draft with its total and say that nothing is purchased. Place the order only after the office manager writes an explicit approval in the draft's thread.
  3. Add a cron trigger weekly-snack-batch to kortix.yaml. It runs the office-snacks agent every Monday at 08:00 with the prompt "Load the snack-batching skill and run this week's snack-batching pass."

  4. Tell me which of these connectors are not connected yet.

  5. Open a change request with all of it. Do not merge it.

2

Connect your tools

Open Connectors in your workspace and connect Slack. Credentials are brokered server-side and never enter the agent's machine. Then add your ordering account's API key as the ORDERING_ACCOUNT_API_KEY secret, granted to this agent only.

Slack

Collects requests and posts the draft order for approval.

Or useMicrosoft Teams
Required
Amazon

Builds the cart within budget and orders only after approval.

Or useInstacart
Required
3

Run it once with this prompt

Merge the change request, then start a session with the office-snacks agent and send this prompt. Check the cart and the total before you let the schedule take over.

Prompt

Run this week's snack-batching pass in #office.

  1. Find your last posted draft order in #office and collect every snack-shortcut request since then.
  2. Merge duplicates into one line each, with the total quantity and every requester.
  3. Add the standing staples: coffee beans, sparkling water and oat milk.
  4. Build the cart on Amazon within $150, and trim the least-requested items first if it runs over. Do not check out.
  5. Post the draft order with its total to #office, and say that nothing is purchased yet.
4

Let the weekly schedule take over

The change request added this trigger to kortix.yaml. From now on the agent runs every Monday at 08:00, each run in a new session on its own cloud computer. To change the time, edit the cron line, or open Triggers in the workspace.

kortix.yaml
triggers:- slug: weekly-snack-batch  name: Weekly snack batch  on:    cron: "0 0 8 * * 1"  run:    agent: office-snacks    prompt: Load the snack-batching skill and run this week's snack-batching pass.
5

Buy nothing without a written yes

The draft post is the only output of the weekly run. The agent checks out only after the office manager writes an explicit approval in the draft's thread. Silence, an emoji or a question is not approval. When the thread is still open at the next weekly run, its items roll into the new batch instead of a stale order.

6

Read the draft order

Each run ends with one draft order in the channel. This is what a run looks like in the session:

Weekly snack batch · Mon 08:00
Load the snack-batching skill and run this week's snack-batching pass.
Worked for 1m 46s
slack · search messages → #officeordering account · search items × 11ordering account · add to cart × 11slack · post message → #office

Collected 14 requests and merged them into 8 lines, plus the 3 standing staples. The cart totals $138.40 against the $150 budget. Nothing is purchased until the office manager approves in the thread.

Illustrative example. Your cart depends on what people request.

The pattern

Collect requests through a Slack channel shortcut, batch them on a cron trigger, keep the vendor and budget rules in skills and memory, and hold the order at a human approval gate before it spends. One place in, one approved order out.

Make it do more

Once it works, paste any of these into the same session.

Suggest new staples

Once a month, list every item requested in three or more weeks and propose it as a standing staple in a change request.

Label dietary needs

Mark each line in the draft order as vegan, gluten-free or contains nuts when the vendor listing says so.

Announce the delivery

After an order is placed, post in #office on the morning it is due to arrive, with the list of what is coming.

Guardrails

Because the agent can prepare an order that spends money, the controls matter even for a small chore:

  • Isolation. Each weekly run executes in its own isolated sandbox, and only the prepared order and Slack post it's explicitly allowed to send are written back out.
  • Scoped secrets. The ordering-account credential is encrypted in the secrets manager and injected into the sandbox at runtime, scoped to the agents you grant them to or the logs.
  • Human approval gates. No purchase is placed until the office manager approves the draft order in Slack.
  • Everything is code. The vendor, the budget, the staples, and the batching schedule are files in the repo — versioned and changed through a reviewed change request rather than a dashboard setting.

The outcome

Requests batched into one order on a schedule
Weekly
Every request comes in through a Slack shortcut
One place
Nothing is purchased without a person signing off
Approve first

Requests stop getting lost, duplicates get consolidated, and the office manager reviews a finished order instead of assembling one. The spending step stays behind a person, so the automation saves the busywork without ever placing an order on its own.

On this page

  • The problem
  • What we built
  • How it works
  • Make it do more
  • Guardrails
  • The outcome

Run this yourself

Install this exact setup — agent, connectors, schedule, and guardrails — in a guided flow.

More use cases.

  • How we handle GDPR data-subject requests on a deadline

    Legal·July 11, 2026

  • OpenChatly

    How we keep our docs in sync with the code

    Documentation·July 5, 2026

  • OpenChatly

    How we QA every pull request automatically

    QA·July 5, 2026

Own your AI.Start today, in our cloud.

Start for free

OpenChatly is the AI workspace for everything. One person directing, agents executing, from goal to finished work.

©2026 OpenChatly AI.沪ICP备2025124785号-5

Resource guide

  • Product overview
  • Skills marketplace

Terms of service

  • User agreement
  • Privacy policy

Contact us