Tutorials and case studies for analysts, builders, and operators across retail, insurance, healthcare, logistics, research, real estate, and civic teams.
Define your own master/sub region hierarchy on top of any boundary set (states, counties, congressional districts, voting precincts, or your own custom polygons). Tag a donor file, sales-customer list, or policy book → every row carries its region plus the full ancestor chain. Aggregate, render, publish. Premium feature, end-to-end walkthrough.
Pick a county where your campaign or program is already strong. Which 50 other counties demographically resemble it? One call to find_similar_areas → cosine distance over normalized Census variables → ranked list ready to target. Premium tier.
A regional health system has 12 clinics in North Carolina and wants to know where to open the 13th. find_underserved_areas gives back the top 20 underserved tracts; render_map with pin_overlays paints them under labels for the existing locations.
Retail-site question, one call. geo_isochrone → population_in_polygon gives total population, median household income, age, and education for the drive-time area. With the system Census cache warm, zero external API calls.
A site-selection director ranks 12 candidate Tampa locations on drive-time demographics and competitor density. Nine steps, about three minutes of wall clock.
How a policy researcher pinned boundary versions, pulled the Census median-household-income variable across 2010 / 2015 / 2020 editions, and shipped a citable URL plus a GeoJSON appendix that any reviewer can re-render.
A five-step tutorial. Real data, real maps, no Python notebook. Walks through geocoding 2,000 donor addresses, joining Census demographics, building a congressional-district map, and auto-generating an explainer paragraph.