Copy-paste prompt
At 9am and 3pm every day, list orders in [store/export] that haven't shipped within [2] business days, and shipped orders whose tracking hasn't updated in 4 or more days or shows an exception. For each, give the cause and draft a short, honest update to the customer. Don't send anything.
Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.
What you need
- Read-only orders export
- Carrier tracking pages
How the agent does it
- List orders unfulfilled beyond your handling time ([2] business days).
- For shipped orders, check tracking; flag no-scan-in-4-days or 'exception'.
- Draft a proactive customer update for each flagged order.
- Summarize counts by cause (not picked, label printed but not scanned, carrier delay).
What you get
A list of flagged orders with the cause and a customer update draft for each.
| Schedule | Twice daily, 9am and 3pm. |
|---|---|
| Needs your approval | Customer messages and any refunds or reships need approval. |
| How to check it worked | Every flagged order has a tracking link or status source. |
Common mistakes
- Messaging customers about orders that are fine. Recheck tracking right before drafting.
Setting it up in each agent
In Grok Bot
Ask the Bot to run the prompt once and review the result. Then say "Save the process we just used as a skill called 'Late and stuck order watch'" and "Create a routine that runs the Late and stuck order watch skill twice daily, 9am and 3pm". Grok Bot's docs say a Bot can own up to 50 routines, schedules must be at least five minutes apart, and you should use Test run before you enable one.
In Meta Muse
Paste the prompt into Muse and ask it to remember the job and run it on the schedule. Muse asks for approval before outbound actions and purchases, so keep the 'don't send' line in the prompt. Before you rely on it, check that Muse can reach the apps this recipe needs.
In ChatGPT Dots
Give your dot the prompt as an ongoing goal and set the schedule. Dots can work between chats and ask for approval before sensitive actions. OpenAI says background work counts toward your plan's allowance, so match the frequency to what you actually need.
Run it by hand once with harmless inputs before you schedule it. A test run does real work.