Copy-paste prompt
Every weekday at 8am, look through my email from the last 30 days. List (1) threads where the other person wrote last more than 2 business days ago, so I owe a reply, and (2) threads where I asked something and haven't heard back in 5 or more days. Draft a short, useful follow-up for each. Skip anyone who already said no. 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
- Email connector
- Optional CRM or pipeline sheet
How the agent does it
- Scan sent and received threads from the last 30 days.
- Find threads where the last message is theirs and is older than 2 business days (you owe a reply).
- Find threads where you asked something and got no answer in 5+ days (nudge due).
- Draft a short follow-up that adds value (a link, an answer, a date), not just 'bumping this'.
What you get
A two-section list each morning, 'you owe a reply' and 'nudge due', with a draft for each.
| Schedule | Weekdays at 8am. |
|---|---|
| Needs your approval | Every send needs approval. |
| How to check it worked | Each item links to its thread; nothing older than 30 days is resurfaced more than once. |
Common mistakes
- Nudging people who said no. Exclude threads that contain a clear decline.
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 'Follow-up and stale-deal tracker'" and "Create a routine that runs the Follow-up and stale-deal tracker skill weekdays 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.