Turn messy addresses into structured data

Fix typos, expand abbreviations, validate before geocoding. The reliable pre-step for agents handling user-typed addresses.

Customer-typed addresses are the worst data in your stack. Postcodes in the wrong field. 'St' that means street or saint. Half-typed locality names. Pasting from PDF brings invisible whitespace. Anything that touches a free-text address field needs a cleanup pass before it can be geocoded reliably.

parse_address takes up to 100 messy entries and returns structured components plus an audit trail of what was a typo, what was an abbreviation, what was inferred. Feed the cleaned output into geocode (single) or batch_geocode (bulk) for coordinates with confidence scores.

Useful for chat support agents resolving service-area questions, sales pipelines deduping leads, and data-engineering jobs ingesting customer CSVs.

Patterns

What this looks like in practice

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

Pre-geocode cleanup

Run a list of customer-typed addresses through parse_address, then feed the structured components into batch_geocode. Match rates lift versus geocoding the raw strings directly.

Service-area lookup for support agents

Customer types 'do you deliver to NW1?' or 'do you deliver to camden town'. Parse, geocode, intersect with your service-area polygon. Answer in one turn.

Lead-enrichment pipeline

Take a CRM export with messy addresses. Parse and batch_geocode in one pass. Use reverse_geocode to enrich with normalised admin hierarchy (locality, region, country) before deduplication.

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 →

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 →

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 →