The Scenario
You are three weeks into a new role at a recruiting firm. Your first assigned project is preparing a candidate database for import into the new ATS. The outgoing recruiter left an Excel workbook with 200 candidates, each with a school name entered freeform on the application. "U of M," "Umich," "University of Michigan-Ann Arbor," "Michigan," "Go Blue State" — all the same school, none in canonical form. The ATS requires a standardized school name and a LinkedIn school URL before it will accept the import. The client review is Friday.
The bad version:
- Build a lookup table of university aliases and run a VLOOKUP against it — covers maybe 60 of the 200 candidates
- Open a browser tab for each remaining candidate, search for the school, find the LinkedIn page, copy the canonical name, paste it into the workbook
- Do this for 140 candidates, making it through 80 before the day ends, leaving the other 60 for tomorrow morning and hoping the client doesn't ask about the import status before noon
You were hired to source candidates and manage relationships. The database cleanup arrived as a bonus assignment nobody budgeted time for.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. 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.
Normalize every university entry in my Excel Candidates table School column using People Data Labs and populate Canonical School Name, Website, and LinkedIn URL.
What You Get
- The Canonical School Name column populated with PDL's standardized institution name
- The Website column populated with the school's primary website
- The LinkedIn URL column populated with the school's LinkedIn page
- Entries that PDL cannot confidently resolve flagged in a Notes column so you can decide whether to hand-verify them or leave them out of the import
What If the Data Is Not Quite Ready
Some entries include degree type mixed in with the school name — "BS from Michigan" or "MBA, Wharton"
Before cleaning, extract only the institution name from each entry in the School column: strip degree labels, graduation years, and any text before or after the school name. Then clean via PDL and populate Canonical School Name, Website, and LinkedIn URL.
The client wants to rank candidates by school tier for the shortlist
Clean each school name via PDL and populate Canonical School Name and LinkedIn URL. Then add a Tier column: "Top 20" for schools that fall in PDL's top program rankings, "Top 50" for the next tier, "Other" for everything else.
Some entries are boot camps or online programs that PDL doesn't have in its database
Normalize each school entry via PDL. For entries PDL cannot resolve, check if the entry contains keywords like "bootcamp," "online," "Udemy," or "Coursera" and flag those rows in the Notes column as "Non-traditional education — manual categorization needed."
Clean school names, add country of institution, and flag international candidates for a diversity report
Clean each school name in the School column via PDL and populate Canonical School Name and LinkedIn URL. Add a Country column using PDL's institution country data. Flag any non-US school in a Diversity Flag column as "International candidate" for the client's reporting.
One prompt resolves the school names, adds country context, and flags international candidates — the ATS import file is complete and the diversity report data is already there.
Try It
Get the 7-day free trial of SheetXAI and open any Excel workbook with a column of freeform university or school names from applications or candidate records. 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.