AGLOW
An automated tracking and coaching tool for group collaboration
An automated tracking and coaching tool for group collaboration
Artificial Social Intelligence (ASI) for Group Learning and Optimization of Collaborative Workflows (AGLOW)
AGLOW is a cross-domain collaboration workflow management system and an AI coach for teams.
When experts come together to solve big challenges, there can be inefficiencies in the group problem-solving process. In the intelligence community, for example, experts have different specialties—each essential—but maximizing their contributions requires significant effort in tracking tasks and updating teammates on the status of the project.
“The tool could let you know what the other people on your team are trying to accomplish without the need for continuous, disruptive status meetings. People could just do their work and the tool infers what they’re doing and tells everybody else.”
![](https://b3069131.smushcdn.com/3069131/wp-content/uploads/2024/06/Leonard-Eusebi_circle-headshot-200x200.png?lossy=1&strip=1&webp=1)
Leonard Eusebi
Senior Scientist and Principal Investigator on AGLOW
The Charles River team is developing software to help improve collaborative work. Artificial Social Intelligence (ASI) for Group Learning and Optimization of Collaborative Workflows (AGLOW) aims to provide automated tracking of team problem-solving activity, and coaching suggestions to streamline group collaboration so that teammates can focus on their work. AGLOW research is based on puzzle hunts—collections of interrelated brain teasers that require diverse knowledge and skills and are a good representation of the type of collaborative problem-solving that experts face in the intelligence community.
“The tool could let you know what the other people on your team are trying to accomplish without the need for continuous, disruptive status meetings. People could just do their work and the tool infers what they’re doing and tells everybody else,” said Leonard Eusebi, Senior Scientist at Charles River Analytics and Principal Investigator on the AGLOW effort.
The solution is designed to work within the secure environment that intelligence analysts are already using for their work. A Microsoft Word Add-in will provide tools to highlight key questions, answers, and insights about a task, while a web interface will collect tasks and summarize behavior. A cognitive architecture will interpret how team members’ behaviors relate to their goals, and an AI coach could provide suggestions to improve team coordination. The Charles River team originally built this ASI coaching system for a Minecraft-based urban search and rescue effort under the DARPA ASIST program, and it now provides an opportunity for future applications in additional domains.
AGLOW will allow teammates to share tasks, goals, and progress through a convenient interface. It is anticipated that AGLOW will save time and lead to better outcomes for collaborative group problem-solving.
Contact us to learn more about AGLOW and our other adaptive intelligent training and artificial intelligence capabilities.
The research reported in this document was performed in connection with contract number W912CG- 23-C-0007 with the U.S. Army Contracting Command – Aberdeen Proving Ground (ACC-APG) and the Defense Advanced Research Projects Agency (DARPA). The views and conclusions contained in this document are those of the authors and should not be interpreted as presenting the official policies or position, either expressed or implied, of ACC-APG, DARPA, or the U.S. Government unless so designated by other authorized documents. Citation of manufacturer’s or trade names does not constitute an official endorsement or approval of the use thereof. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon.