The Scenario
You are a sales ops analyst. Your team spent the last six weeks scraping 500 target company profiles from LinkedIn using PhantomBuster. The company objects are all sitting in PhantomBuster org storage, with employee count, industry, and HQ location attached.
The next outbound push starts Monday. Your SDR manager needs every company scored against the ICP before Friday, and the ICP scoring model lives in a Google Sheet with formulas in columns G through J that run on employee count and industry.
The bad version of this week:
- You export company data from PhantomBuster one CSV at a time from individual Phantom runs
- The CSVs have different column structures because different Phantoms used different field configurations
- You spend Wednesday reconciling the column names and stacking the sheets
- You run the ICP formulas on Thursday and discover 80 rows have missing employee count, which breaks the scoring formula entirely
- You go into the weekend with 20% of accounts unscored and no clean file to hand the SDR team.
The fast version is one prompt.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent inside your spreadsheet that queries PhantomBuster company storage directly, not Phantom run CSVs, so you get the enriched version of the data in a consistent column structure.
Open the SheetXAI sidebar and type:
Search all PhantomBuster company objects and write company name, LinkedIn URL, website, industry, employee count, and HQ location into columns A through F of this sheet.
SheetXAI calls PhantomBuster's company storage API, paginates through all 500 objects, and writes each one into the sheet in the columns you specified. Consistent structure, every time.
What You Get
A flat Google Sheet with all 500 company objects from PhantomBuster storage, laid out exactly for your scoring formulas:
- Column A — company name
- Column B — LinkedIn company URL
- Column C — website
- Column D — industry
- Column E — employee count
- Column F — HQ location
The ICP scoring formulas in columns G through J can run immediately. No column renaming, no stack-and-reconcile session.
Once the data is in the sheet, tell SheetXAI to flag the rows where employee count is missing, or to apply a preliminary ICP tier label based on industry and employee count before the full formula runs.
What If the Data Is Not Quite Ready
Company data from LinkedIn scrapers often has gaps. SheetXAI handles them in the same prompt.
When employee count is stored as a text range instead of a number
PhantomBuster scraped the LinkedIn "company size" field, which returns ranges like "51-200 employees" rather than a clean integer.
Write all PhantomBuster company objects into columns A through F. In column E, convert the employee count field to a midpoint number, so "51-200 employees" becomes 125. Write the numeric midpoint into column E so the ICP scoring formulas can run.
When some companies are missing an industry tag
A batch of 40 companies were scraped without the industry field populated. The scoring model will error on those rows.
Write all PhantomBuster company objects into columns A through F. For any row where the industry field is blank in column D, write MISSING INDUSTRY into column D and flag the row with an X in column G so the team can manually classify them before scoring.
When you only want companies in specific industries
The ICP is narrower than the full scrape. You only want SaaS, fintech, and healthtech.
Search all PhantomBuster company objects and filter to companies where industry contains "software," "fintech," "financial technology," or "health technology." Write name, LinkedIn URL, website, industry, employee count, and HQ location into columns A through F.
When you need to pull, clean, score, and sort in one go before Friday morning
The SDR manager needs the scored file in Slack by 9 AM. No more passes.
Search all PhantomBuster company objects and write name, LinkedIn URL, website, industry, employee count, and HQ location into columns A through F. Convert employee count ranges to numeric midpoints in column E. Flag rows with missing industry in column G as MISSING INDUSTRY. In column H, apply a preliminary ICP score: "Tier 1" if employee count is 51-500 and industry is software or fintech, "Tier 2" if employee count is 501-2000, "Tier 3" for everything else. Sort the sheet by ICP score, Tier 1 first.
The pattern: you pull the data and do the prep work in the same instruction. The file is scoring-ready when the query finishes.
Try It
Get the 7-day free trial of SheetXAI and open any Google Sheet, then ask it to pull your PhantomBuster company objects into the sheet. The PhantomBuster integration is included in every SheetXAI plan. For related workflows, see how to push target accounts back into PhantomBuster storage or the PhantomBuster in Google Sheets overview.