Spatial Thoughts Academy

Agentic Coding for Geospatial gave me a working method. During the course I used an AI coding agent to build a complete building-detection pipeline end to end in a Colab notebook: tiling a very high-resolution drone orthomosaic (3cm), reprojecting each tile to its local UTM zone, resampling to match a pre-trained GeoAI model’s training resolution, running inference, and saving the results as GeoJSON. When the pipeline produced zero detections partway through, the agent diagnosed the actual cause, tiles that had shrunk below the model’s working size after resampling, rather than papering over it, and fixed it. That is the kind of practical, tool-grounded workflow I was looking for. I recommend the course to anyone doing applied GIS work who wants to move faster without losing rigor.

I am very happy to have taken the Cloud Native Remote Sensing with Python course with Ujaval. This is the sixth course I have taken with him, and I will definitely continue learning from him. In my opinion, he is the best educator in the geospatial technology field. He is also an excellent person: kind, approachable, and always willing to help and answer questions, even after the courses have ended. I highly recommend this course and Ujaval as an instructor.

In today’s AI-driven professional landscape, a traditional CV is no longer enough to demonstrate expertise. The real differentiator is showcasing tangible competence through projects, tools and methodologies on a polished professional website.

Ujaval’s “Building Your Geospatial Portfolio Website” course proved to be exactly what I needed. Rather than prescribing a one-size-fits-all solution, Ujaval provides a high-level strategic overview and trusts participants to chart their own path. Whether your background is deeply technical or rooted in project management, the course validates that everyone has meaningful stories worth telling.

Over two days, the experience was transformative. I gained clarity on just how much of my career deserves documentation and realized the potential of translating those experiences into a compelling digital portfolio. What impressed me most was how Ujaval integrated modern tools, particularly how to leverage LLMs for generating markdown content and building automated solutions for website development.

Even more than the nice, friendly class format that Ujaval and Vigna always run, the really cool thing is how the class is current with the relevant, current best practices. For instance, in this class session, what was so nice to learn was the approach to use AI tools in Python programming in a useful, careful, and appropriate way.

What a great course. It’s comprehensive, well-paced, interactive, and Ujaval and Vigna are excellent at delivering its content. So many additional resources are provided as well that pique your curiosity and make you want to continue the QGIS learning journey. I’ve already signed up for another course!

Ujaval Gandhi is an extraordinary, globally recognized teacher who, like all brilliant people, does not need to give himself importance. In this course I had the opportunity to interact with him, the class and his very talented collaborator Vigna receiving answers to all the questions asked. Unlike the self-study tutorials I had the opportunity to receive explanations of the assigned tasks and was shown how each problem can be solved in different ways. In addition to the course material, additional information/explanations and links are given to expand on the topics covered and the recorded lectures are shared so that they can be reviewed to catch missed information during the online course. Qgis is an amazing software, with a fantastic community, deserving of donations, the nightmare of proprietary GIS software.