Copy-paste prompt
Every day at 6pm, check [Gumroad / Etsy] for new sales, buyer messages and refund requests. Draft replies for the messages. Check that every product page loads and its price matches [price sheet]. Send me a short report: today's sales, messages with drafts, anything broken, and one improvement idea. Don't reply to anyone or change anything.
Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.
What you need
- Shop dashboards (browser) or email notifications
- Product files folder
How the agent does it
- Read new sales and messages since the last run.
- Draft answers for buyer questions (download help, licensing, customization).
- Check each product page loads, files download and prices match your price sheet.
- Note top sellers this week and one improvement idea (cover, bundle, price test).
What you get
A daily shop report with sales, messages and drafts, broken pages, and one idea.
| Schedule | Daily at 6pm. |
|---|---|
| Needs your approval | Replies, refunds, price changes and publishing new products need approval. |
| How to check it worked | Sales totals match the platform dashboard; every broken link is reproduced twice. |
Common mistakes
- Automatic refunds. Keep refund decisions with the owner.
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 'Gumroad and Etsy digital shop manager'" and "Create a routine that runs the Gumroad and Etsy digital shop manager skill daily at 6pm". 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.