Launching today

Waldo by Wherobots
The AI agent that accelerates engineering with spatial data
264 followers
The AI agent that accelerates engineering with spatial data
264 followers
Waldo is the geospatial data agent that turns questions about the physical world into answers, maps, and production-ready data pipelines. It analyzes satellite imagery, geometries, geography data, and your organization's first party data, writes and debugs the analysis, and delivers results in hours. When the work needs to run continuously, Waldo turns it into a scheduled pipeline on your existing data platform. Built for spatial analytics at scale by the creators of Apache Sedona.













Free Options
Launch Team / Built With

AWS Activate CreditsCredits that fuel your startup’s next milestone
Promoted



i like how waldo can turn satellite imagery into real insights. Can it also work with custom business data?
@donna_light012 Thanks for the question, yes Wherobots and Waldo can federate access to your first party business data in AWS S3, Databricks, AWS Glue, and any Apache Iceberg compatible catalog service.
This is the part that caught me: Waldo shows its work under "Worked" — the code, runtime, and rows read for each step — instead of just handing back a map. With spatial data I can't eyeball the result the way I can with a UI, that traceability is what would make me trust it. One question: once Waldo builds a pipeline in SpatialSQL/Python, can I take that pipeline out and run or edit it on my own, or does it only live inside the chat?
Congrats on the Launch! How does Waldo fit into an existing data engineering workflow?
@vespertine_dallarosa Waldo can seamlessly integrate within data engineering projects. The physical world context generated by Waldo can then be automatically integrated with generic data workflows. Waldo uses WherobotsDB behind scenes, which can read and write data to popular datalakehouse formats like Iceberg tables / parquet tables as well as major databases like PostgreSQL. That makes it work well with existing data pipelines / workflows. Furthermore, A generic data engineering agent can invoke Waldo to do the data engineering tasks on physical world data at scale.
@abod_rehman thank you for your support! 🚀
@jiaqip @abod_rehman Thanks Abdul! Glad you like it. That is Waldo Tobler's first law of Geography.
@drjiayu making spatial data accessible without heavy coding is a big step. What kind of tasks can Waldo handle best right now?
@drjiayu @urban_sage Waldo is built to handle both large scale spatialSQL and python operations using WherobotsDB, as well as computer vision tasks with RasterFlow, running on aerial imagery.
@drjiayu @urban_sage @benppruden these tasks are just the start. I believe those can serving as building blocks to create agents that understand the physical environment well and take action with that context to achieve difficult missions in real physical environment.
Turning location data into useful answers without heavy coding sounds great. @mo_sarwat How well does waldo handle large datasets?
@velvet_trace Great question. In fact, I asked Waldo how it does that and it asnwered it perfectly and briefly:
Heavy computation runs in Wherobots Cloud, not in the chat.
Data size, coverage, schemas, and coordinate reference systems are checked first.
Early filters limit reads to the columns and files needed.
Compute size is chosen based on the workload and how it will be distributed across compute pods.
Spatial joins and calculations on large physical world run on WherobotsDB in an optimized SQL session behind the scenes, with summaries returned to the chat.
Intermediate results are reused to avoid repeating expensive work.
Query performance is inspected before changes are recommended.