Copy-paste prompt
Every 30 minutes on weekdays from 8am to 6pm, check [inbox / form sheet] for new inquiries. Research each sender's company from their email domain, score them against these rules: [rules], label them hot, warm or not-a-fit, and add a row to [lead sheet]. Draft a reply for each. For hot leads, message me right away.
Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.
What you need
- Inbox or form export
- Your ideal-customer rules
How the agent does it
- Watch for new inquiries in the inbox or form sheet.
- Enrich from the sender's domain: company, size, location, what they likely need.
- Score against your rules (budget, timeline, fit) and assign hot / warm / not-a-fit.
- Draft a reply: book-a-call for hot, a helpful resource for warm, a polite decline for not-a-fit.
What you get
A line for each lead in the lead sheet, an alert for hot leads and a draft reply for every lead.
| Schedule | Every 15-30 minutes during business hours. |
|---|---|
| Needs your approval | Sending replies and booking calendar slots need approval. |
| How to check it worked | Each score lists which rule fired; no lead is dropped (in = out). |
Common mistakes
- Over-eager auto-replies. Draft only, at least until reply quality is proven.
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 'Inbound lead qualification'" and "Create a routine that runs the Inbound lead qualification skill every 15-30 minutes during business hours". 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.