Copy-paste prompt
Every Monday at 8am, write my weekly owner briefing: last week's revenue, orders, refunds, spend and cash, each linked to its source; wins and misses from each agent job's log; everything waiting for my approval, oldest first; and 3 priorities for this week, with a keep, fix or kill call on each experiment. Keep it to one page.
Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.
What you need
- Outputs from your other recipes (logs, sheets)
- Sales and expense exports
How the agent does it
- Collect last week's numbers: revenue, orders, refunds, spend, cash in and out.
- Pull highlights and failures from each agent job's log.
- List every item waiting for your approval, oldest first.
- Recommend 3 priorities for the week, with keep, fix or kill calls on experiments.
What you get
A one-page briefing: numbers, wins and misses, pending approvals and 3 priorities.
| Schedule | Mondays at 8am. |
|---|---|
| Needs your approval | Read-only. It recommends, it doesn't act. |
| How to check it worked | Every number links to its source file; pending approvals match the logs. |
Common mistakes
- Rosy summaries. Require the misses section to be non-empty or say 'none found' explicitly.
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 'Weekly owner briefing (chief of staff)'" and "Create a routine that runs the Weekly owner briefing (chief of staff) skill mondays at 8am". 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.