Skip to content

UPDATED 06:00 EST / NOVEMBER 18 2026

BIG DATA

Exclusive: Wherobots AI agents automate complex spatial data engineering

Cloud-native spatial analytics and artificial intelligence startup Wherobots Inc. today introduced an artificial intelligence agent that enables users to build and deploy spatial data pipelines using natural-language instructions, reducing the need for specialized programming expertise.

Called Waldo, the agent can discover data sources, generate queries, perform analysis, visualize results and schedule recurring operations. It’s designed for applications involving location-based information such as satellite imagery, road networks, GPS tracking data and geographic features.

Spatial data presents unusual processing challenges because it combines multiple data types, including geographic coordinates, imagery and geometric shapes. Analyzing this information at scale often requires specialized tools and scarce technical expertise.

A recent survey by Global Marketing Insights Inc. concluded that the global geospatial workforce is 10 to 15 years behind in building the skill levels employers need.

Wherobots, which was founded in 2022 by the creators of the open-source Apache Sedona spatial analytics engine, said Waldo can compress development projects that traditionally take weeks into days.

“Waldo is our new agentic interface,” said Damian Wylie, Wherobots’ head of product. Unlike general-purpose AI coding assistants, he said, Waldo can invoke specialized computational engines that can process enormous geographic datasets.

“We’re not deploying some net-new [large language model] under the hood,” Wylie said. “We’re connecting existing LLMs to our product and also giving it the context it needs to speed up that spatial data workflow.”

The agent orchestrates several components of Wherobots’ platform. Its Havasu spatial data and knowledge catalog discovers and prepares public geographic datasets alongside customers’ private information. RasterFlow, Wherobots’ serverless Earth intelligence and inference engine,  processes satellite and aerial imagery using computer vision models to identify features such as buildings, roads and land-use changes.

WherobotsDB executes the resulting analysis using more than 300 spatial functions, while Wherobots Maps visualizes the results. Completed pipelines can be scheduled to refresh automatically as new data arrives.

The distributed processing platform uses existing cloud storage and enterprise data catalogs, including Amazon Web Services Inc.’s Glue and Databricks Unity Catalog, eliminating the need for customers to migrate their data, Wylie said.

In a demonstration, he showed how Waldo could identify the drainage area surrounding Montana’s West Boulder River using geographic and elevation data. The agent located relevant datasets, constructed a geographic representation of the watershed and displayed the results on a map.

The resulting geometry could support subsequent analysis of snowfall, water runoff or changing environmental conditions, Wylie said. Waldo can also process satellite imagery using specialized machine learning models, including Meta Platforms Inc.’s Segment Anything Model 3.

Potential commercial applications include identifying delivery vehicles that deviate from planned routes, assessing weather-related transportation disruptions and analyzing advertising impressions based on billboard locations and mobility patterns.

Wherobots said customer Action Engine Inc. is using the technology to build recurring fleet analytics pipelines and reports that it can deliver new spatial analyses two to three times faster that was possible with manual processes. Another customer used the platform’s distributed computing architecture to reduce a large-scale data-joining operation from approximately a week to less than an hour, said Benjamin Pruden, Wherobots’ go-to-market executive.

Waldo isn’t intended to eliminate human oversight, executives said. Users can inspect generated queries, review geographic visualizations and create Jupyter notebooks to examine individual processing steps. Wylie acknowledged that the technology can’t guarantee accurate results from every prompt.

“That’s an area we’ll invest,” Wylie said. “We’re not at the stage where we’re going to say every prompt is the best quality you’ll ever get.”

Waldo is available in public preview, with agent tokens currently included at no additional charge in Wherobots Professional Edition. Customers pay primarily for the computational resources they consume, with controls to select processing capacity and monitor costs.

Image: Flickr CC

A message from John Furrier, co-founder of SiliconANGLE:

Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.

  • 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
  • 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network

Are you an AWS customer?  Support SiliconANGLE financially by buying your AWS services from our Marketplace portal page and links: https://siliconangle.com/aws-marketplace/

 

About SiliconANGLE Media
SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — with flagship locations in Silicon Valley and the New York Stock Exchange — SiliconANGLE Media operates at the intersection of media, technology and AI.

Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.

Send us a news tip

Send us a News Tip

  • This field is for validation purposes and should be left unchanged.
  • Max. file size: 244 MB.

Sign in

SIGN IN

Bio

Ethics statement

Extract the signal from the noise

Get SiliconANGLE updates and analysis.

Contact us

Partner with us

Contact us

Guest inquiry