How It Works Under the Hood

Five Federal Agencies, Live. Three Model Tiers. One Score. In 20 Seconds.

While others spend hours piecing together county records, Buildability™ queries 5 federal agencies live plus commercial data partners in parallel. Each question then routes to the right frontier-model tier based on complexity, all in under 20 seconds.

FoundationIntelligenceReasoningAll systems operational
5
Federal Agencies, Live
3
Frontier Model Tiers
9
Weighted Score Factors
20s
Second Analysis
Architecture

Three-Tier Data Architecture

Live federal queries, commercial enrichment, and model-routed reasoning — one unified pipeline.

01

Foundation Layer

5 Federal Agencies, Queried Live

Direct integrations with official government databases — FEMA flood maps, USGS geological surveys, EPA environmental screens, Census geocoding, and USDA soils. Each of these five federal sources is queried live on every fresh run and cited in the report. Parcel geometry, zoning, and market data come from the commercial partners named in the layer below.

Census Bureau
Geocoding, TIGER boundaries & demographics
FEMA NFHL
Flood zone maps & flood risk
USGS
Elevation, geology & seismic data
EPA
Radon zones & environmental screening
USDA
Soil classification & suitability
02

Intelligence Layer

Commercial & Geospatial Partners

Commercial-grade parcel geometry, ownership records, rental comps, and zoning enrichment, plus open geospatial data. Property-level granularity that federal data alone cannot provide.

Regrid
Parcel boundaries & ownership
RentCast
Rental comps, AVM & market data
Zoneomics
Zoning codes & permitted uses
OpenStreetMap
Infrastructure, utilities & amenities
03

Reasoning Layer

Model-Agnostic Router, Frontier Tiers

The reasoning layer is model-agnostic. A complexity router scores every query and picks the cheapest frontier-model tier that can answer correctly — fast tier for lookups, default tier for reasoning, top tier with long-context and adaptive thinking for due diligence. 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 tier
Long-context · adaptive thinking · due diligence & full-ordinance reasoning
Default tier
Balanced reasoning · where most queries land
Fast tier
Extractions, lookups & conversational replies
Method

Overlay Suitability Analysis, at Parcel Granularity

A 57-year-old peer-reviewed method, operationalized live against federal sources — not a new score invented from scratch.

01

The method, since 1969

McHarg · Design with Nature

Weighted overlay of constraint layers (slope, soil, hydrology, hazard, zoning) to derive suitability for a use. Ian McHarg formalized it in 1969; it is the foundation of every GIS overlay analysis planners have run since.

Design with Nature (1969)
Ian McHarg · the founding text
GIS-MCDA canon
Multi-criteria decision analysis · the modern name
Weighted linear combination
The math your zoning department already trusts
02

The literature we build on

300+ peer-reviewed papers · 3,600+ citations

Malczewski's 2006 survey counted more than 300 refereed GIS-MCDA articles in a fifteen-year window; the paper itself has been cited over 3,600 times. Weighted linear combination with spatially varying weights — what our 9-factor composite reduces to structurally — is textbook. The math is settled; what we operationalize is the pipeline underneath it.

Malczewski (2006)
GIS-MCDA literature survey · 15-year corpus
Spatial sensitivity analysis
How weights are defended
Wharton WRLURI (Gyourko et al.)
The regulatory-index peer at jurisdiction level
03

What is new here

Parcel granularity · hazard + permission · live-cited

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). What we operate is the composite — hazard and permission together, one Buildability Score™ per parcel, sources queried live on every fresh run and cited per finding.

Parcel-level national coverage
All 50 states · not one jurisdiction
Both axes in one score
Hazard + permission composed, not chosen
Live-cited on every run
Every finding traces to its cited source
Pipeline

Address to Score in 20 Seconds

Enter an address — we do the rest.

01

You enter an address

Time: 0s. No manual research, no waiting for county callbacks.

02

We query 5 federal agencies live

Time: ~2s. Every source queried in parallel — Census, FEMA, USGS, EPA, and USDA.

03

Model router picks fast, default, or top tier

Time: ~8s. The cheapest frontier-model tier that can answer correctly handles the reasoning.

04

You get your Buildability Score™

Time: ~20s. Graded, weighted, explained, and exportable.

Reasoning

Model-agnostic —route to what wins the task.

A complexity router picks the cheapest frontier-model tier that can answer correctly — we swap providers when a better model shows up.

Reasoning

01Complexity RoutingA complexity scorer analyzes every query and picks the cheapest frontier-model tier that can answer correctly. Fast tier for lookups, default tier for reasoning, top tier for full-ordinance and due-diligence questions.

02Prompt CachingThe stable property-context prefix (base persona + property data) caches across multi-turn conversations on the same parcel. Only the volatile per-turn content gets repriced. Multi-turn deals stay cheap.

03Confidence, HonestEvery answer is paired with a confidence score derived from data completeness and source agreement. When confidence is low, we surface the uncertainty — we don't paper over it with a fake consensus average.

Model-agnosticConfidence surfaced, not hiddenRouted per query
Security

Security & Compliance

Enterprise-grade security at every layer. Your data never touches a scraper, never trains a model, never leaves our infrastructure.

256-bit TLS Encryption

All data encrypted in transit with TLS 1.3. At rest with AES-256.

CCPA Compliant

Full compliance with California Consumer Privacy Act. Your data, your rights.

No Scraped Data

Every data point comes from official APIs with documented provenance. Never web scraping.

Daily Data Refresh: LivePlatform Uptime: 99.9%SOC 2 Type II: In Progress
Development & AI Architecture

How We Build Buildability™

The reasoning layer is model-agnostic — three tiers (fast, default, top) picked per query by a complexity router. Each tier handles the queries it does best, and we swap in whichever frontier model wins the task.

The router picks the cheapest tier that can answer correctly. Prompt caching on the property-context prefix keeps multi-turn conversations on the same parcel cheap. Every response is grounded in live data from 5 federal agencies.

01

Top tier

Long-context · adaptive thinking

Handles the highest-complexity queries — multi-jurisdiction feasibility, full-ordinance reasoning, investment-grade due diligence. Long-context windows let it reason across overlapping zoning overlays and multi-jurisdictional rules without losing the thread. Adaptive thinking is on for the highest-stakes calls.

02

Default tier

Balanced reasoning

The default. Handles regulatory interpretation, risk assessment, and persona-aware deep answers at a fraction of the top-tier per-token cost. Where most queries land.

03

Fast tier

Low-latency lookups

The fast lane. Handles structured extractions, simple data lookups, and conversational replies that do not need deep reasoning. Cheapest, fastest.

04

Agentic coding

Development

Buildability™'s codebase is architected and developed with agentic coding tools. From the frontend to the API routes, AI-assisted development accelerates every feature.

Stop Guessing. Start Knowing.

Run your first property analysis free — 5 federal agencies queried live, a model-agnostic reasoning router, 9 weighted factors, one score. In 20 seconds.

Analyze a Property — Free

No signup required · Results in 20 seconds