DoD AI Challenge – Creating an Eye in the Sky

Last fall, Excella participated in the Department of Defense’s (DoD) Eye in the Sky AI Challenge. The AI challenge called for the development of Machine Learning (ML) and computer vision algorithms to accelerate the analysis of satellite imagery and enhance disaster response. At Excella, we use technology to make bold new visions a reality, so we felt this was a perfect fit for our vision and mission.

To tackle this AI challenge, Excella formed a small team of experts, gave them a limited set of hours, and asked them to work under Excella Labs, our internal Innovation Engine. They used their Agile expertise to establish cadenced timeboxes, one day each week when the team could collaborate. Each day was divided into a series of iterations where they focused on a small set of deliverables, demonstrated progress, gathered feedback, and planned the next set of objectives.

The team emphasized rapid learning throughout the process. They used DevSecOps to enhance their ML expertise by creating an automated pipeline. The pipeline gave them rapid feedback on their work, its progress, and its quality. They identified unknowns—their largest risks—and prioritized work that would bridge these knowledge gaps. The team built a very solid technical infrastructure that allowed frequent iteration, rapid learning, and continuous improvement. It gave Excella, DoD, and future clients an extremely effective and scalable foundation for rapidly deploying AI/ML solutions with clients in the future.

Eye in the Sky was an excellent opportunity to showcase Excella’s talents while helping to impact the community. Through Excella’s participation in the competition, they were able to develop new technologies, demonstrate how they could enhance disaster response, and validate the best practices they’ve used for their clients to enhance Automated Intelligence efforts using Agile and DevSecOps techniques.

Read our case study to see more about how our team’s approach to Eye in the Sky had the following demonstrable benefits:

• More rapid learning and validation
• Faster time to market
• Improved extensibility