Where to look first.
A probability heatmap of where a missing person is most likely to be found, built from their behavioural profile, the terrain, and current weather.
POST /v1/predictThe problem this solves.
When seconds count, drawing search rings on paper costs daylight. predict is a single HTTP POST that gives the on-call search planner a probability surface in the response format their team already knows. Deterministic and reproducible, suitable for after-action reviews and methodological scrutiny.
What comes back in the response.
- Scored H3 hex grid. Top 50 hexes by default; full grid via include_hexes: true.
- Deterministic. The same inputs return the same surface, every time.
- JSON-shaped response that drops into deck.gl, kepler.gl, QGIS, ArcGIS without transformation.
- Standard POST + x-api-key. Use from Python, Node, Go, or any HTTP client.
- Per-call audit logs available for incident review and FOI responses.
Call it from your backend.
Predictable HTTP. JSON in, JSON out. One auth header. Use it from any backend, edge function, or script.
curl -X POST https://api.footstep.ai/v1/predict \
-H "x-api-key: sk_live_your_key_here" \
-H "Content-Type: application/json" \
-d '{ ... }'Related capabilities.
get_isochroneReachability polygons by time or distance from any starting point. Walking, cycling, or driving.
search_placesPoints of interest near a location, by category or by venue name. Sorted by distance.
parse_addressFree-text in, structured out. Fixes typos, expands abbreviations, infers missing fields, and scores confidence.
Ready to call it?
£5 free credit on signup. One auth header, every major runtime.