This workshop walks through building a filming location site selection use case in CARTO. We'll combine multiple criteria — such as scenery, travel time to major hubs, weather, and state tax incentives — into a single composite score that ranks candidate locations. From there, we'll explore and iterate on that score two ways: interactively in a CARTO Builder map, where you can adjust inputs and see results update, and through a separate agentic chat interface, where you can ask questions in plain language and refine your shortlist on the fly.
Public safety agencies generate enormous volumes of 911 data but most of it stays locked behind analyst-only tooling. This workshop walks through turning 911 call records into an AI Agent that answers “where do we need to respond faster?” in plain English. We'll build a live public safety hotspot map in CARTO Builder, then wire up a conversational agent so any non-technical team member, such as dispatch or operations, can query it themselves.
Last-mile delivery lives and dies at the curb, but most teams can't see where it's actually breaking down. This workshop turns open NYC data into a live view of where delivery pressure is highest across the city. We'll build the analysis in CARTO Workflows, visualize the hotspots in a CARTO Builder map, and wire up an AI Agent so anyone on the team can ask, in plain English, which neighborhoods need attention most.
What if anyone could build a custom geospatial application, with exactly the brand, experience, and features they want? Too often, spatial data gets trapped in generic maps and GIS tools that flatten both the data and the intent behind it, and custom apps used to mean expensive engineering and long timelines. CARTO for Agents moves the starting line: teams go from a blank page to a working custom app in minutes. Join Juan and Alex for a live vibecoding session where you build your own app right alongside them, secure, enterprise-ready, and built to scale, powered by CARTO and deck.gl. Bring an idea, leave with an app!
Insurance organizations manage portfolios of properties, assets, customers, and claims distributed across complex geographies. Understanding where risk is concentrated, how exposures change, and what action to take is critical across home, commercial, utilities, underwriting, claims, fraud, and catastrophe response.
In this hands-on workshop, we will show how to combine policy, property, hazard, claims, and infrastructure data to build a practical insurance risk and exposure workflow. Participants will explore how spatial analysis and GeoAI can help identify risk concentrations, compare locations, investigate patterns, and prioritize action.
The workshop will use Snowflake and CARTO together as a reference implementation. Snowflake provides the governed data, scalable computation, and AI foundation, while CARTO provides the spatial analytics, workflows, maps, and location intelligence experience. The business problems and patterns are broadly applicable to insurers whether they already use Snowflake or are evaluating modern cloud data platforms for geospatial analytics.
This workshop is designed for insurance data scientists, GIS professionals, analysts, and business leaders who want to turn location data into more informed underwriting, claims, fraud, resilience, and portfolio decisions. Participants will leave with a reusable blueprint for applying spatial intelligence across multiple insurance use cases.
5G mmWave signals are highly sensitive to topography, yet traditional raster-based Line-of-Sight (LoS) analysis remains computationally expensive and siloed from the modern data stack. To overcome these barriers, this workshop demonstrates how to transform raw DEM/DTM data into vectorized isobands, enabling massive-scale spatial joins between terrain elevation and network assets. This transition allows telcos to integrate topographic insights directly with customer churn, signal telemetry, and asset management without stitching together point solutions. This workflow can be further streamlined using H3 global grid indexing for simplified data unification. Attendees will leave with a clear roadmap for moving from static raster map-making to dynamic, terrain-aware network intelligence using Databricks and CARTO.
An interactive talk delivering 3D, place-based stories on biodiversity loss, climate pressures, finite resources, and urban growth through three-dimensional storytelling. The audience will witness end-to-end workflows for telling place-based stories at the Anthropocene scale creating powerful narratives that reveal how energy demand interacts with planetary boundaries.
.webp){kind=logo}
This workshop introduces geospatial embeddings – compact numerical representations that encode what's in an image – and shows how they can transform Earth imagery into a searchable, analysis-ready dataset. Using LGND's API, participants will run similarity searches to scan broad areas for features of interest, perform change detection and export results into existing GIS tools.
PlacePulse is CARTO’s geospatial foundation model, built in collaboration with Applied Geographic Solutions (AGS). It represents every location in the United States as a 256-dimensional embedding that captures its structural characteristics, combining hundreds of demographic, business, economic, health, and environmental variables into a single vector. These embeddings enable workflows such as similarity search, clustering, segmentation, and predictive modeling.
This hands-on workshop introduces PlacePulse Embeddings and shows how they can be used to accelerate geospatial analysis. We will start with the fundamentals of how the model is trained, then move into practical workflows including finding structurally similar areas, screening markets nationwide, filling data gaps, and applying models beyond the regions where they were originally trained. The session will also demonstrate how PlacePulse can be exposed to an AI agent through CARTO for Agents, enabling users to go from a question to a map, analysis, and working application built on the embeddings.
