Software Engineering
<- Return to all blogs
-
Introducing the new Agentic Queryable Earth: Conversational, Composable, and Traceable
We discuss the evolution of Queryable Earth into Agentic Queryable Earth, including a more conversational experience.
-
Introducing the new Agentic Queryable Earth: Conversational, Composable, and Traceable
We discuss the evolution of Queryable Earth into Agentic Queryable Earth, including a more conversational experience.
-
Is Zarr the New COG? Round 2!
We revisit the question: is Zarr the new COG? We review changes from the past year and discuss the shrinking gap between the two data formats.
-
De-Risking AI: A Roadmap for AI Integration in Finance and Other Highly Regulated Industries
For businesses operating in highly regulated industries, zero risk tolerance policies often lead to delays in AI adoption. Although there are certainly risks that accompany irresponsible AI use, with intentional implementation AI has the potential to boost productivity, reduce risk, and increase profits. Furthermore, failing to implement AI is a risk of its own in…
-
ChatGSFC: Building Composable AI Tools for NASA on Open Source Tooling
Sharing our findings from the past year helping NASA build and scale a chat-based AI tool called ChatGSFC.
-
Building Conversational Interfaces for Querying and Analyzing Geospatial Data
NOAA maintains thousands of datasets of various kinds (remote sensing, in-situ, derived etc.) across multiple domains (climate, weather, ecology, etc.) consumed by a wide variety of users (scientists, engineers, urban planners, etc.), but discovering, accessing, and using these datasets remains a significant challenge. Recent developments in cloud-native geospatial technologies and standards have made geospatial data…
-
Building and Validating LLM-Generated Captions and Embeddings for Geospatial Imagery in Queryable Earth
At Element 84, we’ve been exploring how LLMs can improve geospatial imagery search. We recently published a blog post detailing our latest updates to our Queryable Earth demo which lets users search for visible features on the Earth using natural language. Until recently, it relied entirely on SkyCLIP, an open-source vision-language model, to generate the…
-
(Re)Making Cirrus: Three lessons learned
In part two of this blog series reflecting on our work with Cirrus, we discuss three core lessons that we uncovered.
-
If AI Is Going to Task Satellites, We Need Standards
It’s been about a month since North51 in Banff. For those who haven’t been, it’s a unique event on the geospatial calendar. It’s a small, single-track conference that fosters great group discussions rather than broadcasting lectures. There are no sales pitches here, just geospatial people staring at the same mountain range, trying to figure out…
-
(Re)Making Cirrus: Reflections on five years spent building an open-source data orchestrator
This post is based on the author’s talk (Re)Making Cirrus: Five Years Building a Data Orchestration Framework, presented at FOSS4 NA 2025 and FOSS4G 2025. We’ve remade Cirrus at least three times. Maybe four, depending on how you count. Cirrus, a data orchestration framework we develop and use here at Element 84, recently celebrated its…
-
AI Coding and the Future of Open-Source Geospatial Software
In an episode of Star Trek: The Next Generation, Commander Data (an android), creates a new android, Lal. His creation, paralleling the new generation of AI-assisted tools, extends her creator’s capabilities but also begins to operate autonomously. Lal begins to learn, evolve, and act independently, faster than Data can fully guide her. Eventually, she is…
