Routes, stops, and reach for AI travel agents

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.

AI travel agents have to handle the full mess of itinerary building. Place name to coordinates, coordinates to a route, route to nearby attractions, attractions back into a time budget. Most of that is geospatial primitives stitched together at runtime.

Footstep ships those primitives in shapes the model can reason over. find_and_route handles 'directions to the closest castle from here' end to end. search_along_route surfaces ranked detours along an existing path. get_isochrone answers 'what can I reach from this hotel in 30 minutes on foot?'

Pair with compare_routes when the agent needs to recommend between walking and cycling. Pair with get_elevation when terrain matters for a hiking leg.

Patterns

What this looks like in practice

Common shapes mapped to the tools you'd reach for.

Daily-time-budget itinerary

Given a hotel and a 6-hour walking budget, build an isochrone, search for landmarks inside, and route between the top three picks. Returns a polyline you can drop into a map view.

Detour discovery

Pass an existing route and a category like 'cafe' or 'viewpoint'. Get back ranked candidates with detour seconds and where they sit along the route, so the agent can offer options without breaking the schedule.

Mode comparison

When the user asks 'should I walk or cycle?' compare_routes returns both options with distance, duration, and terrain difficulty side by side, plus a one-sentence summary.

Other use cases

Search, rescue, and crisis response

Research Preview

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 →

Real estate and property

Geocode listings, model commute reach, score nearby amenities, and overlay terrain risk. The toolkit behind agent-led property search.

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 →