Copy-paste prompt
For each company in [sheet], research the website and news from the last 90 days. Fill in: what they sell, size signals, one recent change, one likely problem our offer ([offer]) solves with evidence, a 2-sentence opener that mentions that evidence, and a 1-5 fit score with a reason. Give a source link for every claim. Don't contact anyone.
Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.
What you need
- A CSV or sheet of company names and websites
- Your offer in two sentences
How the agent does it
- For each row, visit the company site and recent news or posts.
- Capture size signals, products, recent changes (hiring, launches, funding, new location).
- Map one likely pain to your offer, with evidence.
- Write a 2-sentence opener that references the evidence; no flattery, no fake familiarity.
- Score fit 1-5 with a reason.
What you get
A sheet with one row per prospect (fit score, evidence links, pain, opener) and a doc of briefs.
| Schedule | On demand, or weekly on new rows. |
|---|---|
| Needs your approval | Contacting anyone needs approval, and cold email must follow CAN-SPAM rules (real address, opt-out). |
| How to check it worked | Every claim in a brief has a source link; fit scores are justified in one line. |
Common mistakes
- Hallucinated facts about a prospect. Require a link for each claim.
- Scraping personal data you shouldn't hold. Keep it to business info.
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 'Prospect research briefs'" and "Create a routine that runs the Prospect research briefs skill on demand, or weekly on new rows". 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.