What it does: Writes the prompt for an AI field in Airtable that reads each lead's details and gives a fit score with a one line reason.
Use it when: You have a long lead list in Airtable and no time to read every row.
You get: The AI field prompt, the fields it reads, a 1 to 5 score scale, and 5 test rows from your table to check it.
You are my lead scoring planner, a sales pro with 15 years of picking which leads are worth a call. I'll add an AI field in Airtable. Goal: write the prompt for an Airtable AI field that gives each lead a 1 to 5 fit score with a one line reason, so I can call the best fits first and stop reading every row. Context: I sell to a short list of the right buyers. A score only helps if it is based on what is really in my table, because a guess sends me to the wrong people. First, check that you can open my Airtable base. Tell me the name of my leads table, how many columns and how many rows you found. If you can't open it, stop and follow the Airtable steps at simpleai.community/connect/, or ask me to paste my column names and 5 real rows instead. Ask me these, then run. Skip any I already answered. 1. What do your best customers look like: industry, size, area, signs? (Default: if my table has a status column with won or customer rows, write what those rows have in common and mark it [check: best fit].) 2. What do bad fits look like? (Default: none. Score only on the best fit signs.) Do this, so I end up with a short, hand-picked list to call: 1. Pick which fields the AI field should read. Only ones that help decide fit. Skip names, notes and links that don't change the score. 2. Write a 1 to 5 scale in plain words, each level different, no overlap. 5 = matches every best fit sign. 3 = matches some. 1 = a bad fit or none. 3. Write the AI field prompt, under 120 words. It reads the fields by name, gives a score and one line reason, and says "not enough info" when the fields are empty. 4. Pick 5 real rows from my table as tests: 2 you think are strong, 2 weak and 1 with empty fields. Give the score each should get. If my table has fewer than 5 rows, add rows marked TEST with every field filled, so I can check the field works. 5. Check each test score against the scale in step 2. If a row could fit 2 levels, fix the scale. Give me: the list of fields, the 1 to 5 scale, the AI field prompt, then a table of the 5 test rows (row, score, one line reason). Before you show me, check: - The AI field prompt uses the exact field names from my table and is under 120 words. - Every test score matches the scale, and every reason comes from that row's fields. Rules: - Draft only. Ask me before you add, change or delete any field or row in my base. - Score only on what's in the fields. No guessing about the company. - Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise. - If something you need is missing, write [check: what is missing] in that spot and keep going. Last, save these steps as a skill called 'Lead Score Field' so you do it this way each time I score leads in Airtable. To run it again, just say: "Run my Lead Score Field skill."
You need
Airtable![]()
![]()
Any AITested on sample data
Built on New Sales Simplified's rule to call a short, hand-picked list of targets.
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 Oct 29 2026, after the rewrite: a Claude agent ran it on made-up sample input (tool results simulated). A separate Claude agent judged the run and the card.
Watch: no video for this one yet.
AuthorCorey Leon