Tangram – Fully Automated Intelligence Analysis Support


The TANGRAM program, managed by the US Air Force Research Lab at Rome is developing a fully automated intelligence analysis support system to continuously process intelligence information from classified and unclassified sources, rapidly detecting suspected terrorist activities. To date, many of the intelligence analysis programs have focused on systems, tools and algorithms to suspected activities and events of interest. They relied on prior knowledge about known terrorists, groups, affiliations and activities, to tracking terrorist suspects and detecting their threat event intentions. Current analysis methods are searching large data banks for patterns of terrorist behaviors. Current procedures are effective, yet despite recent improvements, the total production time for a single answer is currently measured in days and weeks. To have any demonstrable improvement in the intelligence process we need to provide answers in hours or minutes.

The Tangram program will address fundamental challenges limiting current technology. The new processes will be x100 times more productive and x100 times faster discovering threat entities, delivering high quality intelligence and improve the probability of detection of low observable threats and events, where “guilt by association” assumptions may not apply.

However, to achieve their potential, we must develop the processes, procedures and standards to deploy a fully automated, analytic system capable of processing tens of thousands of simultaneous analytic inquiries in an efficient and scalable manner.