The Scenario
You are a marketing analyst. Last month the team ran a product usage survey — 300 respondents, all of whom entered their job title in a free-text field. The titles are everywhere: "Sr. Product Manager," "product mgr," "PM," "Head of Product," "Principal PM." Your segmentation model requires a normalized title with seniority level and department before you can run the analysis the CMO asked for. The report is due Thursday.
The bad version:
- Write a regex-based title normalizer that maps common abbreviations to full forms — it handles 60% of the cases and produces wrong seniority labels for anything with "Senior" vs. "Sr." vs. "Snr."
- Manually review and fix the remaining 120 rows that the regex misclassified or didn't match
- Hand off the dataset to the analyst running the segmentation model and get a message an hour later saying the seniority labels are still inconsistent
You're the one who built the survey. You're also the one cleaning up after it.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Google Sheet. 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.
For each raw job title in column A, enrich it via PDL job title enrichment and write the cleaned title, seniority level, and department into columns B, C, and D.
What You Get
- Column B populated with PDL's cleaned, canonical version of each title
- Column C populated with the seniority level from PDL's taxonomy — IC, Manager, Director, VP, C-level, and so on
- Column D populated with the department classification — Engineering, Marketing, Sales, Operations, Finance, etc.
- Rows where PDL cannot confidently classify the title flagged in column E for manual review before the segmentation run
What If the Data Is Not Quite Ready
Some titles include company name or team name mixed in — strip those first
Before enriching, clean column A: remove anything after a comma or after "at" that looks like a company or team name. Then run PDL job title enrichment on the cleaned titles and write canonical title, seniority, and department to columns B, C, and D.
You want to group by department for the segmentation model
Enrich each title in column A via PDL and write cleaned title, seniority, and department to columns B, C, and D. Then add a column E grouping label for the segmentation model: "Technical" for Engineering and Product, "Revenue" for Sales and Marketing, "Support" for Operations and Customer Success, "Finance and Legal" for those departments.
Some respondents entered their previous title by mistake — flag senior titles that don't match their LinkedIn
Enrich each title in column A via PDL and write cleaned title, seniority, and department to columns B, C, and D. If the seniority is C-level or VP but the respondent listed their email domain as a personal Gmail or Hotmail, flag the row in column E as "Title may not match current role — verify."
Normalize titles, segment, and count respondents per seniority band in one prompt
Enrich each title in column A via PDL and write cleaned title, seniority, and department to columns B, C, and D. Then add a summary tab showing the count of respondents per seniority level and per department.
One prompt normalizes the titles and builds the summary the CMO is waiting for — no second aggregation step.
Try It
Get the 7-day free trial of SheetXAI and open any Google Sheet 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.