BuildabilityHow it works under the hood
7 federal agencies, live. One formula. Three model tiers to explain it.
While others spend hours piecing together county records, Buildability™ queries every source in parallel and scores it with one formula, in about 20 seconds. Geo answers the follow-up questions on the model tier you choose.
Foundation · Intelligence · Reasoning
Architecture
Three-tier data architecture.
Live federal queries, commercial enrichment, and model-routed reasoning. One unified pipeline.
Foundation layer
7 federal agencies, queried liveDirect integrations with official government services: FEMA flood maps, USGS terrain and seismic, USDA soils, USFS wildfire, EPA radon and water systems, and Census geocoding. Each is queried live on every fresh run and cited in the report.
- CensusGeocoding · TIGER boundaries · block groups
- FEMANFHL flood zones · SFHA designations
- USGSSeismic hazard · 3DEP terrain & slope
- EPARadon zones · community water systems
- USDASSURGO soils · suitability ratings
- USFSWildfire Hazard Potential
- USFWSNational Wetlands Inventory
Intelligence layer
Commercial, city and open sourcesCommercial-grade parcel geometry, ownership records and rental comps, each city’s own zoning map and code, plus open geospatial data. Property-level granularity that federal data alone cannot provide.
- RegridParcel boundaries and ownership
- RentCastRental comps, AVM and market data
- City zoning layersEach city’s published zoning map
- Zoning AtlasDimensional standards quoted from the ordinance
- OpenStreetMapInfrastructure, utilities and amenities
Reasoning layer
Model-agnostic, three frontier tiersGeo answers on the tier you choose, the balanced tier by default, and steps down to a cheaper tier as an account nears its monthly AI allowance. Prompt caching on the property-context prefix keeps multi-turn conversations on the same parcel cheap. We swap providers when a better model wins the task.
- Top tierLong-context, adaptive thinking, due diligence and full-ordinance reasoning
- Default tierBalanced reasoning, where most queries land
- Fast tierExtractions, lookups and conversational replies
Method
Overlay suitability analysis, at parcel granularity.
A 57‑year‑old method from the planning literature, operationalized live against federal sources. The Score itself is not peer reviewed.
- 01
The method, since 1969.
Weighted overlay of constraint layers (slope, soil, hydrology, hazard, zoning) to derive suitability for a use. Ian McHarg formalized it in Design with Nature in 1969. It is the foundation of every GIS overlay analysis planners have run since; GIS-MCDA is its modern name, and weighted linear combination is the math your zoning department already trusts.
- 02
The literature we build on.
Malczewski's 2006 survey counted more than 300 refereed GIS-MCDA articles in a fifteen-year window. Weighted linear combination with spatially varying weights, which our nine-factor composite reduces to structurally before the landmine caps apply, is textbook. The math is settled; what we operationalize is the pipeline underneath it. The regulatory-index peer at jurisdiction level is the Wharton WRLURI (Gyourko et al.).
- 03
What is new here.
Prior productizations solved one axis at a time: hazard-only at scale (First Street, on every Realtor.com listing) or permission-only at jurisdiction level and periodic (WRLURI, Terner CLU). We operate the composite: hazard and permission together, one Buildability Score™ per parcel, all 50 states, sources queried live on every fresh run and cited per finding.
Pipeline
Address to Score in 20 seconds.
Every source queried in parallel, one formula, cited per finding.
- 0s
You enter an address.
No manual research, no waiting for county callbacks.
- ~2s
We query 7 federal agencies live.
Every source queried in parallel: Census, FEMA, USGS, EPA, USDA, USFS, USFWS.
- ~8s
The engine scores it.
One formula: min(weighted composite, every landmine cap). No model inside the number.
- ~20s
You get your Buildability Score™.
Graded, weighted, explained, and exportable.
Reasoning
How we build Buildability™.
The reasoning layer is model-agnostic. Geo explains the Score and answers follow-ups; it never computes it. Three tiers, and we swap in whichever frontier model wins the task.
Geo runs on the tier you pick, the balanced tier by default. As an account nears its monthly AI allowance, it steps down a tier instead of cutting you off.
The stable property-context prefix (base persona plus property data) caches across multi-turn conversations on the same parcel. Only the volatile per-turn content gets repriced.
Scores and parcel facts come from the engine’s own tool output, never the model’s memory. When a tool has no data, Geo says so instead of filling the gap.
Top tier
Long-context · adaptive thinkingMulti-jurisdiction feasibility, full-ordinance reasoning, investment-grade due diligence. Long-context windows reason across overlapping zoning overlays without losing the thread. Adaptive thinking is on for the highest-stakes calls.
Default tier
Balanced reasoningRegulatory interpretation, risk assessment, and persona-aware deep answers at a fraction of the top-tier per-token cost. Where most queries land.
Fast tier
Low-latency lookupsStructured extractions, simple data lookups, and conversational replies that do not need deep reasoning. Cheapest, fastest.
Buildability™'s codebase is architected and developed with agentic coding tools, from the frontend to the API routes.
Security
Security and compliance.
Your data never trains a model. Addresses go only to the processors listed on /compliance.
Encrypted in transit and at rest
All data encrypted in transit (TLS 1.2 minimum, 1.3 preferred) and at rest with AES-256.
CCPA compliant
Full compliance with the California Consumer Privacy Act. Your data, your rights.
Read from the publisher
Federal and commercial records arrive through their own services. City codes are read from the published ordinance by BuildabilityBot, which obeys robots.txt.
The methodology, on any parcel.
Weighted overlay analysis since 1969, at parcel granularity, cited live to source. See what it returns for an address.
Free to score · Property Report $99 · ~20 seconds · For cities and counties: see what your city has