Spatial intelligence for property search
Geocode listings, model commute reach, score nearby amenities, and overlay terrain risk. The toolkit behind agent-led property search.
Property search is going agentic. Buyers ask 'find me a three-bed in Bristol with a 30-minute commute to Temple Meads and a decent pub within walking distance.' That question decomposes into geocoding, isochrones, POI search, and a few filters.
Footstep gives the agent each primitive. Geocode listings on ingest. Compute reach polygons from each candidate to the workplace, school, or station the buyer cares about. Search nearby for amenity categories. Pull elevation and grade to flag flood-plain or hillside risk before the agent recommends a viewing.
All outputs are GeoJSON-ready, so the candidate set drops straight into a Mapbox GL or deck.gl viewer for the buyer to browse.
What this looks like in practice
Common shapes mapped to the tools you'd reach for.
Commute-reach filter
Compute a 30-minute drive isochrone from each candidate listing to the buyer's workplace. Filter the catalogue to listings that fall inside.
Amenity scoring
Search for nearby cafes, schools, gyms, and parks within 1km of each listing. Score the listing on amenity density and category mix.
Terrain risk flag
Pull elevation and grade for each listing's coordinates. Flag flood-plain risk (low elevation near rivers) or steep-access risk for hillside properties.
Bulk listing import
Run a CSV of new listings through batch_geocode to anchor coordinates and normalise labels. Failed rows return typed errors so you can fix and re-run.
The Footstep tools that fit this shape
A focused subset of the catalogue. Click any card for the full reference.
geocodeConvert an address or place name to coordinates with a confidence score.
get_isochroneEverywhere reachable within a time or distance budget. Returns a polygon boundary.
search_placesFind points of interest near a location by category or name.
get_elevationElevation values for coordinates or paths, with summary statistics.
batch_geocodeGeocode up to 1,000 addresses in a single call.
Other use cases
Search, rescue, and crisis response
Score where a missing person is most likely to be found. Direct ground teams to the highest-density hexes first.
Read →Logistics and autonomous fleets
Multi-stop optimisation, OD matrices, and corridor search for the agents and backends that move things.
Read →Environmental and field operations
Terrain profiles, reachability polygons, and GPS map matching for ESG reporting, conservation, and field research.
Read →Travel and itinerary planning
Find places, route between them, fit them into a time budget, and surface what's on the way. The geospatial layer behind agentic trip planners.
Read →Customer-input cleanup
Fix typos, expand abbreviations, validate before geocoding. The reliable pre-step for agents handling user-typed addresses.
Read →Field service and dispatch
Optimise visit order, score reachable jobs from each tech, clean GPS into proof-of-visit records.
Read →Insurance and risk underwriting
Anchor addresses, layer terrain and elevation, assess access from emergency services. Bulk-process portfolios in one call.
Read →Healthcare access and equity
Compute drive-time and walk-time access to facilities, model coverage gaps, place ambulances with travel-time matrices.
Read →Sales and territory planning
Build OD matrices between reps and accounts, draw catchments around offices, normalise lead addresses at scale.
Read →Outdoor and fitness apps
Plan walking, hiking, and cycling routes with explicit difficulty. Snap noisy GPS into clean traces with surface and grade per edge.
Read →Public-sector planning
Model who can reach what, where the gaps are, how transit changes the answer. Reachability and matrix tools for civic planning.
Read →