The Scenario
You work at a recruiting firm. A client handed you a Google Sheet with 200 candidates — names, schools they attended, and graduation years. The school names were entered freeform on the application form. You've got "U of M," "Michigan," "University of Michigan Ann Arbor," and "UMich" all in the same column, all meaning the same school. Your ATS requires a canonical institution name and a LinkedIn school URL before you can import the records. The client wants the import done by end of week.
The bad version:
- Run a VLOOKUP against a university reference table you cobbled together from a previous project — it covers 40 of the schools on the list
- Manually look up the remaining 160 schools one at a time in PDL or LinkedIn, copy the canonical name and URL back into the sheet
- Find that some entries like "State School" or "Online Program" don't have clear PDL matches and decide to leave them blank, hoping the ATS won't reject them on import
You spend the better part of two days doing work that should take two minutes. And the ATS still rejects 12 records at import because you left the ambiguous ones blank.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Google Sheet. It reads the school name column and uses PDL's school cleaner to resolve each entry to a canonical institution name, website, and LinkedIn URL.
Clean each school name in column A via PDL and write the standardized school name, website, and LinkedIn profile into columns B, C, and D.
What You Get
- Column B populated with the canonical school name from PDL's education database
- Column C populated with the school's primary website
- Column D populated with the LinkedIn school page URL
- Entries that PDL cannot confidently resolve flagged in column E so you can review them before the ATS import
What If the Data Is Not Quite Ready
Some entries include degree type mixed in with the school name
Before cleaning, strip degree terms — BS, BA, MBA, MS, PhD — from each entry in column A. Then clean the remaining school names via PDL and write canonical name, website, and LinkedIn to columns B, C, and D.
The client wants to know which schools are in a specific tier for ranking purposes
Clean each school name in column A via PDL and write canonical name and LinkedIn to columns B and C. Then flag schools in column D using a tier label: "T10" for top-10 programs, "T50" for top-50, and "Other" for everything else, based on the canonical name.
Some rows have a city instead of a school name because candidates left the field ambiguous
For each entry in column A, attempt to clean it as a school name via PDL. If the result does not look like a school — for instance if it resolves to a city or returns no match — flag the row in column E as "Ambiguous — review before import."
Normalize schools, add country of institution, and flag international candidates in one pass
Clean each school name in column A via PDL and write canonical name, website, and LinkedIn to columns B, C, and D. Use the school's country from PDL to add a column E country label, and flag any non-US school in column F as "International" for the client's diversity tracking.
One prompt resolves the school names, adds country context, and flags international candidates — the ATS import file is ready without a second pass.
Try It
Get the 7-day free trial of SheetXAI and open any Google Sheet with a column of freeform university or school names. Ask it to clean each one via PDL and write canonical names and LinkedIn URLs back. Then see how to normalize raw job titles with PDL seniority enrichment or go back to the People Data Labs overview.