Prosper Global, formerly Mercy Corps, is using a multi-agent AI system called VERA to shorten research cycles for teams working in conflict zones. Built with Cloudera and running on AWS with Anthropic models, VERA deploys specialized agents that pull data from sources such as ReliefWeb, the ACLED conflict tracker, and local news. A final agent assembles the findings into a draft that analysts can refine. Aaron Eubank, director of data science, stressed that the output is a starting point, not a finished report, so researchers retain agency. In Sudan the tool reduced desk research for an agricultural report from five or six days to two, saving about $1,500. In Colombia a staff member without a security background produced an election security report in a few hours. VERA is also operating in the Democratic Republic of Congo and Ukraine. Officials emphasize a measured rollout because risks differ by location.
Prosper Global, formerly Mercy Corps, is using a multi-agent AI system called VERA to shorten research cycles for teams working in conflict zones. Built with Cloudera and running on AWS with Anthropic models, VERA deploys specialized agents that pull data from sources such as ReliefWeb, the ACLED conflict tracker, and local news. A final agent assembles the findings into a draft that analysts can refine. Aaron Eubank, director of data science, stressed that the output is a starting point, not a finished report, so researchers retain agency. In Sudan the tool reduced desk research for an agricultural report from five or six days to two, saving about $1,500. In Colombia a staff member without a security background produced an election security report in a few hours. VERA is also operating in the Democratic Republic of Congo and Ukraine. Officials emphasize a measured rollout because risks differ by location.