The Scenario
It's 8:45 AM Tuesday. Your pipeline review starts at 9. You've got 200 rows of company names and website URLs in an Excel workbook — leads your SDR team collected last week — and the sales director just asked whether the list skews toward early-stage or mature companies. Founding year, employee count, HQ city. None of that is in the workbook. It's on each company's public website.
The bad version:
- Open each company URL, hunt for an "About" page or LinkedIn link, find the founding year if it's listed, switch back to Excel, enter it into column C, repeat
- Run AgentQL queries manually for the first 20 rows, realize the response schema varies between company types, and spend the next 20 minutes figuring out why column D has headquarters addresses for some rows and employee ranges for others
- Give up on columns D and E entirely and go into the 9 AM meeting with partial data, or just say the enrichment will come "later today"
The pipeline review is in 15 minutes and nobody hired you to transcribe LinkedIn profiles row by row.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. It reads the data in your worksheets, connects to AgentQL to query each company's web presence, and writes the enrichment data back into the right columns — without you touching a single cell manually.
For each company URL in column B, use AgentQL to extract founding year, HQ city, and employee count and write the values into columns C, D, and E
What You Get
- Column C: founding year as a four-digit integer where available
- Column D: HQ city (city name only, not full address)
- Column E: employee count or range as found on the company's public site
- Column F: a "scrape failed" flag for rows where AgentQL returned no data, so you can follow up manually rather than leaving blank cells that look like zeros
What If the Data Is Not Quite Ready
Some rows have missing or malformed URLs
Skip rows in column B that contain no valid URL, scrape company data for the rows that do have URLs using AgentQL, and write founding year, HQ city, and employee count into columns C, D, and E — leave the skipped rows blank
The employee count comes back as a range ("51–200") and I need a midpoint number
For each company URL in column B, extract the employee count using AgentQL, convert any range values to their numeric midpoint, and write the result into column E
I want to join the enriched data with the lead score already in column G
Use AgentQL to pull founding year and HQ city for each URL in column B, then write the values into columns C and D, and add a combined segment label in column H based on employee count in column E and lead score in column G
The company website, the CRM notes, and the ICP checklist are in separate worksheets — enrich the list and flag ICP fit in one pass
Pull founding year, HQ city, and employee count from AgentQL using URLs in the 'Leads' worksheet column B, join with ICP criteria in the 'ICP Criteria' worksheet, and mark each company as ICP fit or not in column F of the 'Leads' worksheet
One prompt handles the enrichment and the scoring logic at the same time.
Try It
Get the 7-day free trial of SheetXAI and open an Excel workbook with a column of company domains, then ask it to enrich each row with metadata using AgentQL. Related: scraping competitor pricing into an Excel workbook or the AgentQL overview hub.