The Scenario
It's your third week running sales ops cleanup. Someone merged two lead lists — 800 rows where column A has names pulled from Salesforce and column B has names from a purchased lead list — and column C is supposed to say whether each pair is the same person. Nobody built that. You inherited the sheet.
The bad version:
- Write a fuzzy-match formula in Excel or Sheets, realize it flags "Jonathan Smith" vs "Jon Smith" as different because the threshold is too tight, and "David Miller" vs "David Miller Jr." as the same because it's too loose
- Manually review the edge cases row by row, realize there are 200 edge cases
- Export to a Python script using a fuzzy library, get results that are inconsistent with the formula results, now you have two conflicting outputs and no single source of truth
You're supposed to be building the routing logic, not reconciling two broken deduplication attempts.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Google Sheet. It uses the Tisane entity comparison tool to evaluate each name pair and write a verdict directly back into your sheet.
For each row, compare the name in column A with the name in column B using Tisane's entity comparison tool and write 'Same', 'Different', or 'Uncertain' into column C
What You Get
- Column C filled with one of three values per row: "Same", "Different", or "Uncertain"
- "Uncertain" is used for cases where Tisane identifies partial overlap — a nickname vs. a full name, or a name with a suffix — rather than forcing a wrong binary answer
- Rows where either column A or column B is blank get a blank in column C, not an error
What If the Data Is Not Quite Ready
The name columns have inconsistent formatting (extra spaces, all-caps, mixed case)
Before comparing names, normalize both column A and column B by trimming whitespace and converting to title case, then run Tisane entity comparison and write the verdict into column C
The source columns are labeled differently — 'CRM Name' and 'Import Name'
Use Tisane to compare person names in the 'CRM Name' column vs the 'Import Name' column and add a 'Match' column with the verdict — include a brief note in a 'Match Notes' column for any row marked 'Uncertain'
Only rows marked 'Unverified' in column D need comparison
For rows where column D says 'Unverified', compare the names in columns A and B using Tisane entity comparison and write the verdict into column C — leave all other rows untouched
Full pipeline: compare, flag uncertain rows, and move them to a review tab
Compare names in columns A and B using Tisane for all 800 rows, write the verdict into column C, then copy all rows where column C is 'Uncertain' to a new tab called 'Needs Review' for manual follow-up
The cleanup and the triage happen in one instruction.
Try It
Get the 7-day free trial of SheetXAI and open any Google Sheet with two name columns you need to reconcile, then ask it to run entity comparison across the whole list. To continue cleaning your lead data, see how to detect language per row or strip HTML from a text column. The full Tisane overview is at the hub.