Brian Impact Foundation
BEES for fellowship candidate discovery and review
Brian Impact Foundation reviewed over 20,000 fellowship candidates with Claude, per Anthropic
Problem
The foundation relied on expert referrals and manual research to identify prospective fellows. Its small team lacked the resources to search more widely.
Approach
The foundation built BEES using Claude to extract and summarize candidate information from public web material. Its web application organized information against assessment criteria for human reviewers.
Results
Takeaway
BEES expanded candidate discovery while leaving assessment with reviewers.
Categories
- Size
- Small business
- Industry
- Professional services
- Business function
- Internal work and knowledge management
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Built in-house
- Evidence
- Vendor case study
Sources
Source summaries
Anthropic described BEES's candidate research and application-review workflows. It reported over 20,000 candidates reviewed and 3 times as many reviews per candidate.
Full details are in the original sources.