The Scenario
Your team ran a product survey last quarter — 300 respondents, free-text job title field. The analysis you promised the VP of Marketing by Thursday requires normalized titles broken into seniority level and department before you can run the segmentation. You're looking at the Excel export. The titles are everywhere: "Sr. PM," "senior product manager," "Principal Product Manager," "Head of Product," "Product Lead." Your regex-based normalizer handles the obvious cases. The rest require judgment calls you don't have time to make manually.
The bad version:
- Extend the regex normalizer to cover more patterns — spend two hours adding rules for "Head of," "Lead," "Principal," and every abbreviation your team uses
- Still end up with 60 rows the normalizer can't handle, which you manually fix one at a time
- Hand the segmentation dataset to the analyst and get a message an hour later saying the seniority labels are inconsistent because your manual fixes used different conventions than the regex output
You promised a dataset. What you delivered was a dataset that still needs another pass.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. It reads the raw title column and uses PDL's job title enrichment to normalize each entry and write back a cleaned title, seniority level, and department.
Enrich every title in my Excel Survey Responses table Job Title column using People Data Labs and fill in Cleaned Title, Seniority, and Department columns.
What You Get
- The Cleaned Title column populated with PDL's canonical version of each title
- The Seniority column populated with PDL's seniority classification — IC, Manager, Director, VP, C-level, or similar
- The Department column populated with PDL's department taxonomy — Engineering, Marketing, Sales, Operations, Finance, etc.
- Rows where PDL cannot confidently classify the title flagged in a Notes column so you know exactly what still needs review before Thursday
What If the Data Is Not Quite Ready
Some titles have a company name or team name appended
Before enriching, strip any text after a comma or after "at" that looks like a company or team name from the Job Title column. Then run PDL title enrichment on the cleaned titles and populate Cleaned Title, Seniority, and Department.
You want to group respondents by function for the VP's segmentation view
Enrich each title in the Job Title column via PDL and populate Cleaned Title, Seniority, and Department. Add a Function column for the segmentation: "Technical" for Engineering, Data, and Product departments, "Revenue" for Sales and Marketing, "Ops and Support" for Operations, Customer Success, and Support, "Finance and Legal" for those departments.
The VP wants a count of respondents per seniority band as a summary tab
Enrich each title via PDL and populate Cleaned Title, Seniority, and Department. Then add a Summary worksheet showing the count of survey respondents per seniority level and per department.
Normalize titles, add a function group, filter out student and intern responses, and summarize in one pass
Enrich each title in the Job Title column via PDL. Populate Cleaned Title, Seniority, and Department. Remove any row where the PDL seniority is Intern or Student. Add a Function column using the grouping above. Add a Summary sheet with respondent counts by Function and Seniority.
One prompt handles normalization, filtering, grouping, and summarization — you send the VP a workbook she can present, not one that still needs a data cleaning note at the top.
Try It
Get the 7-day free trial of SheetXAI and open any Excel workbook with a column of raw job titles from a survey or CRM export. Ask it to enrich each title via PDL and write canonical title, seniority, and department back. Then see how to deduplicate a merged contact list with PDL identity resolution or go back to the People Data Labs overview.