←新闻详情

SiliconANGLE更新于 10月30日 22:50

Prosper Global 用 Cloudera 多智能体引擎 VERA 加速危机研究

Agentic AI helps Prosper Global speed crisis research - SiliconANGLE A

AI 导读

Prosper Global(原 Mercy Corps)基于 Cloudera AI Studios 构建的多智能体研究引擎 VERA,将苏丹一份农业报告的案头研究从五六天缩短到两天,节省约 1500 美元。VERA 于 6 月上线,调用 Anthropic 模型,数据源包括 ReliefWeb、冲突追踪项目 ACLED 和本地新闻,目前已在刚果民主共和国和乌克兰运行。Prosper Global 数据科学总监 Aaron Eubank 强调,VERA 只提供研究起点,最终判断仍由分析师掌握。

正文

Humanitarian groups working in conflict zones are finding that agentic AI can shorten the research cycle between a crisis and an informed response.

Cloudera Inc. has built its AI strategy around deployment flexibility, and one nonprofit partner is testing that approach on the front lines. But the aim is to give analysts a faster starting point, not to automate research, according to Aaron Eubank (pictured), director of data science at Prosper Global, formerly Mercy Corps.

“It’s not the final report that’s going to be pushed out to the humanitarian community and teams, but rather a starting point that analysts can use to continue to iterate on their own research,” Eubank said. “We want to keep the agency in the hands of the researchers themselves.”

Eubank spoke with theCUBE’s Rebecca Knight and Paul Gillin at EVOLVE26, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how multi-agent AI is accelerating humanitarian research, VERA’s early results in conflict zones and the importance of keeping researchers in control. (* Disclosure below.)

Agentic AI meets the humanitarian fog of war

Prosper Global works in about 30 countries with communities facing conflict, climate change and economic hardship. Its crisis analysts’ research could take days to weeks, so the organization built VERA with Cloudera, a multi-agent research engine that uses Cloudera AI Studios, runs on Amazon Web Services Inc. and taps models from Anthropic PBC. Agents pull from sources such as ReliefWeb, conflict tracker ACLED and local news, and a final agent assembles the findings, Eubank explained.

“Agents allow us to really kind of tailor the process for how this research is done,” Eubank said. “Then it will allow us to then add further resources in the future and really have a curated research process that we wouldn’t have had with some of the earlier iterations of generative AI.”

In Sudan, VERA cut desk research for an agricultural report from five or six days to two, saving about $1,500, Eubank noted. In Colombia, an employee with no security background produced an election security report in a few hours. VERA, launched in June, also runs in the Democratic Republic of Congo and Ukraine.

“The risks and the contexts are different in each place that we work,” Eubank said. “It’s important to really take a measured and slow approach as we go through that.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of EVOLVE26:

(* Disclosure: TheCUBE is a paid media partner for the EVOLVE26 2026 event. Neither Cloudera, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE

来源

SiliconANGLE