The Scenario
You're evaluating 50 candidate sites for a franchise rollout. Each one is a real address your ops team has scouted — and now headquarters wants to know which locations have the highest competitor density within walking distance before the final shortlist gets submitted. Someone exported the addresses into a Google Sheet with lat/lng pairs pre-calculated in columns A and B. That sheet has been sitting in your inbox for two days.
This is the third time this quarter you've been handed a location-scoring project without a clear tool for it.
The bad version:
- Manually search Foursquare for nearby venues around each coordinate, record the count in column C, and copy the top venue names into column D — one row at a time
- Realize halfway through that "nearby" was never defined in the brief, so you've been using different radius assumptions for different rows
- Finish the count for 30 sites before the weekly sync, present incomplete data, and get asked why the other 20 aren't done
The shortlist decision isn't waiting for your process to catch up.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Google Sheet. It reads your data, understands the coordinate pairs, and uses Foursquare to run the proximity search across every row in one pass.
For each lat/lng pair in columns A and B, search Foursquare for nearby places within 500 meters and write the total venue count into column C and the top 3 venue names into column D
What You Get
- Column C receives the total number of Foursquare POIs within 500 meters of each coordinate
- Column D receives a comma-separated list of the top 3 nearest venue names by distance
- All 50 rows complete in one operation — no partial results, no mid-list radius drift
- You can then sort by column C to rank sites by competitor density immediately
What If the Data Is Not Quite Ready
The radius requirement changed — stakeholders want counts for both 250m and 1km, side by side
For each lat/lng pair in columns A and B, search Foursquare for nearby venues within 250 meters and write the count into column C, then search within 1 km and write that count into column D
The brief specifies only coffee shop competitors, not all venue types
For each lat/lng pair in columns A and B, search Foursquare for nearby coffee shops within 500 meters and write the total count into column C and the top 3 venue names into column D
Some rows are missing lat/lng — use the address in column E to geocode first, then run the search
For rows where columns A and B are blank, derive lat/lng from the address in column E, then search Foursquare for nearby venues within 500 meters and write the count into column C and the top 3 venue names into column D
Score each site on a 1–10 scale based on competitor count, then flag any site scoring above 7 as high-competition
For each lat/lng pair in columns A and B, search Foursquare for nearby venues within 500 meters, write the raw count into column C, convert the count to a 1–10 score into column D using a scale where 0 venues = 1 and 20+ venues = 10, and flag any row with a score above 7 in column E
Ask for the search, the scoring logic, and the flag in one prompt — it's faster than doing them in sequence.
Try It
Get the 7-day free trial of SheetXAI and open any Google Sheet with lat/lng columns for candidate sites, then ask it to search Foursquare for nearby POIs and score each location. Also worth reading: Bulk Enrich Addresses With Venue Data and the Foursquare hub overview.