Planetary-scale answers, unlocked.
A Hands-On Guide for Working with Large-Scale Spatial Data. Learn more.
Authors
You can now ask Claude questions about the physical world and get answers grounded in real spatial data.
The Wherobots Spatial AI Assistant, now available in the Anthropic Connectors Directory, answers these questions in plain language and returns results, maps, and reports directly in your Claude conversation.
Wherobots is the AI context engine for the physical world. It gives AI the spatial intelligence it needs to reason about where things are, how they relate, and what has happened on the ground.
Here is an example of an insurance risk analysis of all of Colorado that we initially built with Claude Opus 5 and the Spatial AI Assistant, then expanded on with the VSCode Spatial AI Coding Assistant to be a complete hosted application.
The challenge with traditional data systems for building an application like this is both the skills and the data processing cost. We were able to easily join Regrid parcels with Overtures buildings, build hexes that show various layers of risk derived from open raster data, along with the underlying geometry scored on each parcel in a matter of minutes with a Wherobots large runtime. Having the infrastructure and processing capability at you and your AI’s “fingertips” to build with makes moving from idea to production application far easier and faster than without.
Screening indicators from modelled and tract-resolution inputs — not underwriting. Counts are floors. Imagery is locational context only. Open full screen ↗
Getting started with the Spatial AI Assistant takes two steps: install the connector, and sign in to your Wherobots organization, and then begin to prompt Claude. With zero additional setup, Claude can begin to utilize datasets including:
See it in action here:
Analyzing open datasetsThe Wherobots Global Hub continues to expand the open datasets it offers out of the box. In the near future we plan to add wildfire risk models to the hub in partnership with the USDA Forest Service as well as the national hydrography dataset (NHD). You can also connect to STAC collections for additional raster datasets. If there is open or proprietary data that you are interested in having access to fully supported and maintained by Wherobots while iterating with Claude’s models, reach out to us about it.
Analyzing proprietary datasetsIn a few steps, customers can easily attach Wherobots to their S3 storage buckets, catalog systems like Databricks Unity Catalog and AWS Glue Data Catalog, and authoritative 3rd party datasets like Regrid’s Parcels. These integrations enable Wherobots to query proprietary mobility, customer, and asset data with Claude.Once you’ve connected Wherobots every Claude conversation can query the data Wherobots has access to, so you can test your ideas and drive progress with physical world data.
The Spatial AI Assistant plugs into the Wherobots Spatial SQL API and uses skills for accessing the Wherobots documentation, as well as the datasets registered in the Wherobots Global Hub. Claude uses Wherobots skills packaged with the connector to write strong, valid spatial SQL with (generally) correct functions, syntax, and joins. Results come back into your Claude conversation, ready to work with, and you don’t need to interact with a roadmap or a team of spatial experts to get it.
There’s a 14 day/$95 free trial available to all first time users to Wherobots that you can utilize to test your ideas. After the trial expires, customers pay a low on-demand rate for Wherobots spatial units consumed through the Spatial SQL API. When you start your trial let us know you have connected the Spatial AI Assistant and you can qualify for an additional $250 in Wherobots credits.
Getting started is easy. Install Wherobots Spatial AI Assistant for Claude, connect your Wherobots organization, and ask your first question like: How much of Austin’s rooftop area sits under canopy?
Want to see what this looks like in practice before you install? Watch the MCP demos in the videos below. The workflows shown there, from natural language questions to working spatial SQL to results on a map, are the same workflows the Spatial AI Assistant puts in front of your entire organization.
Key takeaways
It is a Claude connector that answers questions about the physical world with real spatial data and returns results, maps, and reports in the conversation. Wherobots is the AI context engine for the physical world.
Install the connector from the Anthropic Connectors Directory and sign in to your Wherobots organization. Then prompt Claude. An example: How much of Austin’s rooftop area sits under canopy?
With zero additional setup: Overture buildings, transportation, and places; Foursquare Open Places; NWS Watch/Warnings updated hourly; GLO-30/90 DEM elevation rasters; and a Regrid parcels sample. You can also attach S3, Databricks Unity Catalog, AWS Glue Data Catalog, and third-party datasets like Regrid parcels.
It plugs into the Wherobots Spatial SQL API and uses skills for Wherobots documentation and Global Hub datasets. Claude uses those skills to write spatial SQL, and results come back into the Claude conversation.
RasterFlow is now available in Public Preview
RasterFlow makes planetary-scale earth intelligence workflows easy and costs predictable. We are excited to announce that RasterFlow is now in Public Preview, opening up the power of planetary scale Earth Intelligence to all Wherobots Professional Edition customers! RasterFlow let’s you solve complex monitoring challenges with vision-language models or tailored models for specific use cases, without […]
Wherobots for QGIS: Cloud-Scale Spatial Data, from Wherobots Labs
Wherobots for QGIS is a new plugin that connects QGIS to Wherobots Cloud. From a panel inside QGIS, an analyst can run spatial SQL against WherobotsDB, load the results as a map layer, push a local layer up to a Wherobots Iceberg table, and pull raster data into the canvas. Why Wherobots for QGIS: Eliminating […]
How Wherobots builds with NVIDIA to let AI see the physical world
The world and what happens in it is digitized by petabytes of raw and derivative spatial datasets of various data types and scales, and the potential for applying AI to it is immense. But the AI models and agents we use every day need connectivity to tools that turn this data into usable insights and relationships. Wherobots gives AI the ability operate on and understand raw physical-world data, and NVIDIA GPUs are core to it. Architecturally here’s how this works at a high level.
El Niño 2026, atmospheric rivers, and California’s burn scars: one SQL engine, two data models
7,713 mapped building footprints sit inside or within 500 m (1,640 ft) of the 42 Eaton basins USGS rates high hazard for debris flows, and 388 km (241 mi) of mapped road and path cross the low ground below the scar. WherobotsDB finds both in SQL: a join to the USGS basins for the buildings, and a raster vector join over elevation for the roads.
share this article
Awesome that you’d like to share our articles. Where would you like to share it to:
