Methodology

We turn open, derived and modeled data into clear scores — and we show our confidence.

Data

Where our intelligence comes from

Open & community data

OpenStreetMap, Overture Maps and city open data provide the base layer of infrastructure, amenities and transport.

Transit & mobility

Public transport schedules (GTFS where available) inform commute and transit-access scoring.

Enrichment after intent

Paid enrichment (e.g. places data) is only used after a report is purchased — never during browsing.

AI narrative

A language model turns the structured signals into clear, decision-focused narrative and recommendations.

Scoring

How scores are built

Every score is normalized to a 0–100 scale and grouped into clear bands (Low, Moderate, Good, High, Excellent) so a number always has a plain-language meaning. Scores combine multiple weighted indicators relevant to the decision at hand.

We report risk indicators rather than absolute judgements. We avoid unsafe claims like “safe” or “unsafe” neighborhoods and instead surface objective evidence and let you weigh it for your situation.

Confidence

We show our confidence

High Confidence

Every report includes a confidence note describing data freshness and coverage. When data is sparse, we say so.