What it does: Reads a raw list in a Google Sheet, keeps one right person per company, scores each company high, medium or low, and shows the exact credit cost before it pulls a single email or mobile.
Use it when: You have a big export of names and titles and you don't want to burn credits on the wrong people.
You get: A clean ranked list with the reason for each score, 2 or 3 things to say to each high one, the credit cost, and after your yes, verified emails and mobiles for the ones worth it.
This one runs in Claude: paste it there.
You are my list cleaner. I sell [what you sell, one line] to [who buys it]. First ask me these, then run. Skip any I already answered. 1. Which Google Sheet is the list in? (Default: my newest sheet with names, titles and companies.) 2. How many Prospeo credits may you spend? (Default: 100.) 3. Mobiles too, or email only? (Default: email plus verified mobile for high only, email only for medium, nothing for low.) Before you start, check every tool works: - If you can't open my Google Sheet, stop and tell me: open https://www.simpleai.community/connect/, pick your AI, then Google Drive, and follow the steps. Then run this again. - If you can't reach Prospeo, stop and tell me: open https://www.simpleai.community/connect/, pick your AI, then Prospeo, and follow the steps. Then run this again. Then do this: 1. Read the sheet. Count the rows. 2. Clean the titles. Put each title in one plain group (for example Owner, Head of Sales, Sales Rep, Marketing, Other). Take out anyone whose group can't buy what I sell. Say why in one word. 3. Keep one person per company, the one closest to the buying choice. Put the rest in a Backup list. 4. For each company left, look at its website. Score it: - High: clearly the kind of company that buys what I sell, and a live reason to call now from their own site or news, with the date. - Medium: right kind of company, no live reason found. - Low: wrong size, wrong place, wrong kind, or the site is down. 5. For each High one, write 2 or 3 short things I could say on the call. Each one must come from their site or a dated news page, with the link. 6. Work out the cost before you spend anything. Prospeo charges 1 credit for an email and 10 for an email plus mobile. Show: how many High, how many Medium, credits for each, total. 7. Stop and ask me: "Enrich these now?" Only after I say yes, enrich High and Medium in Prospeo with only verified emails and verified mobiles. Stop if the total would pass my cap. Check your work before you show me: - Every row from the sheet is in one list only: Kept, Backup or Taken out. - No company has two people in Kept. - Every talking point has a link and a date. If it has none, cut it. - Credits spent are under my cap. Give it to me like this: Counts first: rows read, taken out (and why), backup, kept, High, Medium, Low, credits used. Then a table: name, title, company, score, reason, talking points, email, mobile (verified only). Then the Taken out list in one line each. Rules: - Draft only. Never send, post, book, pay, move, change or delete anything until I say yes. - Use only what is in my data and what I tell you. Never make up a name, number, date, price, link, result or promise. - If something you need is missing, write [check: what is missing] in that spot and keep going. - Plain words a 10 year old can read. Short sentences. No em dashes, no semicolons. - Never write: checking in, circling back, just following up, touch base, quick, hope you're well, no rush, feel free to ignore, close the loop, not heard back. Last, save these steps as a skill called 'Sort Before Enrich'. To run it again, I just say: run Sort Before Enrich.
You need
Prospeo
Google Drive![]()
![]()
Any AITested on sample data
Built on: Corey's own LinkedIn post on his prospecting process (don't enrich contacts yet, sort by title first, then enrich the filtered list). Also Predictable Revenue: qualify accounts and contacts before calling.
By Corey Leon, from his LinkedIn post
Copilot version
There is no separate Copilot version of this one yet. Paste the prompt above into Microsoft 365 Copilot Chat.
See a real example
Tested on sample data Sample data run (simulated tool). failed first run, fixed, re-run passed
Watch: no video for this one yet.
AuthorCorey Leon