Bridging the gap between spatial data and AI
Can AI actually work with spatial data? Complex vector layers, large-scale imagery, spatial relationships — most AI systems weren’t built with any of this in mind. Getting geospatial data to work in modern AI workflows is still a real infrastructure problem.
Felt and Wherobots are teaming up to show you how to solve it. You’ll learn how to make your spatial data AI-ready, push processed datasets straight to maps, and query complex spatial data using natural language.
- How to structure spatial data for AI using Apache Sedona and the Wherobots engine
- How to process datasets in Wherobots and push them instantly to Felt maps
- How to use the Wherobots MCP server to query spatial data with natural language
- How to turn raw raster imagery into AI-ready features for real-world use cases
Speakers
Jaime Sanchez
Director of Partnerships·Felt
Jaime leads Felt’s go-to-market and product relationships with leading Data & AI service providers such as AWS, Snowflake and Databricks. Jaime brings a strong foundation in computer science and over 10 years of GTM experience in geospatial tech which helps drive our strategy of bringing cloud native GIS to our customer’s infrastructure.
Matt Forrest
Director of Customer Engineering & Product Led Growth·Wherobots
Matt is a geospatial educator, author, and developer advocate focused on modern GIS and large-scale spatial data. He writes and teaches on topics ranging from Spatial SQL to cloud-native geospatial workflows, and reaches 70,000+ practitioners through his newsletter. Before joining Wherobots, he spent nearly a decade in the geospatial space building data pipelines and tooling. He’s the author of Spatial SQL (O’Reilly) and a core advocate for Apache Sedona.
Bring your data, see it on the map
Connect a database or drop in a file and see your data live on a map in minutes.