It's almost time for FedGeoDay and we can't wait! Jason Gilman will be presenting his lightning talk: Agentic Context Engineering with Large Federal Datasets and we're looking forward to connecting with folks across disciplines who are tackling similar problems in their work. If you're headed to Maryland next week too, come say hi and let us know what talks you're most looking forward to! Check out the full program here: https://lnkd.in/eZ7m55Yg
Element 84
IT Services and IT Consulting
Alexandria, VA 5,882 followers
Accelerating and scaling impactful projects with great software and design. Geospatial, cloud, and petabyte-scale data.
About us
Element 84 solves challenging problems across a wide range of projects and industries, but our super power is cloud-based geospatial data processing and Earth science systems. We were founded by husband-and-wife engineers in 2010 and have grown into a skilled group of practitioners building high performance user interfaces, software, and cloud systems for the biggest corporate and government clients in the world. Our main office is located in Alexandria, VA but we support a large remote workforce from Michigan to Texas and Pennsylvania to California.
- Website
-
https://www.element84.com
External link for Element 84
- Industry
- IT Services and IT Consulting
- Company size
- 51-200 employees
- Headquarters
- Alexandria, VA
- Type
- Privately Held
- Founded
- 2010
- Specialties
- Agile Software Development, Mobile Development, Clojure, Usability, UI/UX, Visual Design, User Experience, Cloud Computing, Earth Science, DevOps, Geospatial, React, JavaScript, AWS, and Azure
Locations
-
Primary
Get directions
210 North Lee St.
Suite 203
Alexandria, VA 22314, US
Employees at Element 84
Updates
-
This week we attended our first #GoodTechSummit, and it was an awesome opportunity to connect with other mission-oriented organizations. During sessions we were excited to hear people looking to open source and data standards to solve complex challenges in their work. Similarly, we appreciated the nuanced discussions that were held surrounding AI in the nonprofit space. Throughout the summit, speakers focused on the importance of longevity, quality, and impact in our work. As AI continues to proliferate, intentional discussions surrounding how it can be the most impactful without reducing quality are more important than ever. This was a new conference for us -- are there any events you're attending in the next few months that you're particularly excited about? We'd love to hear about them!
-
-
Element 84 reposted this
How is AI accelerating our path to a sustainable presence on the lunar surface? By turning 'What if?' into reality. Jason Gilman just shared a great look under the hood of ChatGSFC, a tool that has been heavily utilized in our work on lunar regolith additive manufacturing (ISRU-AM). I'll never forget that day in the lab: 'I can print a square, a circle, and a straight line. I bet ChatGSFC can help write the script to turn a picture of a railroad track into process-specific toolpaths to additively manufacture one from regolith. Let's find out!' This kind of composable tooling has completely supercharged the nature of innovation for us, helping us constantly redefine the near-impossible.
I'm excited to share a new blog post about ChatGSFC, a NASA internal chat-based AI tool that we've been building and scaling for over a year and a half. More than 7,000 people across NASA's centers use it for everything from risk analysis and mission planning to generating robot instructions for constructing structures from lunar regolith. This has been the main focus of my work for the past year. Maintaining a tool that supports NASA's operational needs and the sheer variety of use cases across the agency has been one of the most challenging and rewarding things I've worked on. The core design philosophy is about composability — putting powerful, flexible building blocks in users' hands rather than building custom applications for every new need. Think Lego, not a pre-assembled toy. We built it on LibreChat, an open-source AI platform, because the same principles that make open source valuable in geospatial technology, transparency, adaptability, freedom from vendor lock-in, apply to AI tooling. For a science and engineering agency where reproducibility matters, the tooling around AI shouldn't add more opacity. As I wrote in the post: "In some ways, this is the dream job for me. I've spent a long time thinking about how to build tools for builders, which is a throughline in my career. ChatGSFC is a realization of that interest. It's about helping the people who do NASA's work accomplish more, get unstuck, and move faster." The blog post goes deeper on the architecture, lessons learned, what surprised us, and why building on open source has been key to making this work. Link in the comments.
-
Andrew Pawloski is in DC today and tomorrow at #ClimateTechConnect26! We're soaking in valuable insights from organizations considering the intersection of climate and technology from all angles, and we're looking forward to even more impactful conversations on day 2 of the conference. If you're here too, come say hi to Andrew and share how you're centering climate resilience in your work.
🌍 Are you ready for ClimateTech Connect 2026???⚡ 🔥 🌊 The conversations that shape our future are happening on April 8–9 April 8th-9th in Washington, D.C. at the Gaylord National Harbor Resort. We've added MORE leaders to our list of Masterclass speakers attending this year’s conference - leaders from insurance, finance, government, and climate intelligence who are driving innovation and resilience across industries. A big welcome to Chrissy Thom of Chubb, Charles Qian of Citi, Tyson Echentile - SAS and Roni Deitz, PE of Arcadis 👏 🎯 Also taking to this year’s stage are: Patrick (Rick) Keegan — Chief Enterprise Underwriting Officer, Travelers Sarah Kapnick — JP Morgan Casey Kempton — Nationwide Raghuveer Vinukollu — Munich Re Roy Wright — Insurance Institute for Business and Home Safety Denise Garth — Majesco Steve Bowen — Gallagher Re Kelly Hereid — Liberty Mutual Sean Kevelighan — Insurance Information Institute Melissa Hoffer — Commonwealth of Massachusetts Angela Grant — Palomar Francis Bouchard — Marsh Jing Liao — Solera Robert Pick — Tokio Marine Veronika Torarp — PwC Rich Sorkin — Jupiter Intelligence Markus Waniek — Munich Re Omar Issa — ResiQuant Lisa Wardlaw — Oliver Wyman Steve Weinstein — CEO & Founder, Mangrove Property Insurance Emilio Figueroa — Head of Insurance, Eventual Treasury Peter T. Gaynor CEM® — Former FEMA Administrator Samuel Broomer - NormanMax Insurance Solutions Stephen Bennett - Mercury Insurance Juan Mazzini - Celent Anil Vasagiri - Swiss Re Garrett Bradford — Milliman Daniel Kaniewski Dr. Ron Dembo - RiskThinking AI Illya Azaroff, FAIA Azaroff, - American Institute of Architects Spencer Glendon - Probable Futures Tracey Wright Laws - RAA Rebecca Harned - Research Institute Fire Safety Check out our incredible agenda for the conference here: https://lnkd.in/e3Bv2Qau #ClimateTech #ClimateRisk #InsurTech #ClimateInnovation #Resilience #ClimateAdaptation #ClimateTechConnect
-
Our latest blog from Jason Gilman details our work helping NASA build and scale a chat-based AI tool called ChatGSFC. In the blog, we discuss how ChatGSFC is comprised of composable parts including: 🏊 Access to a diverse pool of Large Language Models (LLMs) from multiple vendors. 🗃️ File understanding across many formats. 📊 A personal database with user managed tables for structured data exploration. 🛠️ User-created agents with customizable system prompts, models, and tool access. 🏬 An Agent Marketplace that provides a place for users to share and find agents shared by others. ✨ Generative UI, via Artifacts, which allows the LLM to generate web applications that run right in ChatGSFC to display interactive graphics, reports, and information. ⛓️ MCP (Model Context Protocol) as the extensibility mechanism — connecting to other NASA systems and adding new capabilities over time. Read more about why this is so exciting in Jason's post below, and check out the full blog here: https://lnkd.in/eFRezyzQ
I'm excited to share a new blog post about ChatGSFC, a NASA internal chat-based AI tool that we've been building and scaling for over a year and a half. More than 7,000 people across NASA's centers use it for everything from risk analysis and mission planning to generating robot instructions for constructing structures from lunar regolith. This has been the main focus of my work for the past year. Maintaining a tool that supports NASA's operational needs and the sheer variety of use cases across the agency has been one of the most challenging and rewarding things I've worked on. The core design philosophy is about composability — putting powerful, flexible building blocks in users' hands rather than building custom applications for every new need. Think Lego, not a pre-assembled toy. We built it on LibreChat, an open-source AI platform, because the same principles that make open source valuable in geospatial technology, transparency, adaptability, freedom from vendor lock-in, apply to AI tooling. For a science and engineering agency where reproducibility matters, the tooling around AI shouldn't add more opacity. As I wrote in the post: "In some ways, this is the dream job for me. I've spent a long time thinking about how to build tools for builders, which is a throughline in my career. ChatGSFC is a realization of that interest. It's about helping the people who do NASA's work accomplish more, get unstuck, and move faster." The blog post goes deeper on the architecture, lessons learned, what surprised us, and why building on open source has been key to making this work. Link in the comments.
-
It's the first day of #GoodTechSummit26! We're so excited to be in DC learning about impactful and inspiring work from a variety of sectors. If you're here too, let us know and say hi to Catherine Oldershaw!
-
-
It's Friday and our latest quarterly newsletter is out in the world!! 📬 🚀 We share more about: 🌎 Updates to our Queryable Earth demos 🔮 The future of agentic AI and the open source ecosystem 🗓️ Our Spring conference calendar! 🤝 Open roles on our team Check it out: https://lnkd.in/e5eRqqGV
-
-
As geospatial data becomes increasingly accessible, how can we also make it trivial to query and analyze the same data using modern large language models? In this blog, Adeel Hassan details our ongoing open-source work to answer this question as part of a NOAA-funded study. "The goal is to build a natural-language interface that allows users to not only search for datasets (“show me datasets related to sea surface temperature”), but also extract arbitrary insights from them (“What are the trends in sea surface temperatures around near-coast gulf waters over the past several decades?”) and get factually-grounded answers derived from real data that are not only correct and comprehensive, but also include detailed provenance information so that users may verify them." Learn more: https://lnkd.in/eQVSBaGf
-
In our latest blog post we kick off a technical deep-dive into Queryable Earth. 🔍 🌎 We discuss our process captioning Queryable Earth tiles, validating our results, and comparing the embeddings generated by SkyCLIP, Claude Haiku, and Claude Opus. We're excited to continue refining these systems and implementing these ideas in new and exciting ways! Check out the full blog and let us know your thoughts, or if you're interested in using these capabilities in your own work in the future. https://lnkd.in/eJ6UvxUR
-
Earthsearch powers.... a wildflower bloom forecast tracker!! 💐 🌼 🪻 🌷 It's always the highlight of our week when we see a creative new way our work is being used in the wild! In this case, biologist Stephen Klosterman developed an experimental forecast of flower blooms in California's Antelope Valley using Sentinel-2 satellite imagery from Earthsearch. A super cool use case, and a great reminder to take a moment to stop and smell the wildflowers. Check out Leaftime: https://lnkd.in/giAS3sGV And learn more about Earthsearch here! https://lnkd.in/eUbjwUvm
-
