← Cases
South KoreaProfessional services2023 – ongoing

Brian Impact Foundation

BEES for fellowship candidate discovery and review

Brian Impact Foundation reviewed over 20,000 fellowship candidates with Claude, per Anthropic

WorkingVendor case studyVendor ↗

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

over 20,000candidates reviewed, compared with 200 the previous year, per AnthropicVendor case study[1]
3xreviews per candidate compared with the previous process, per AnthropicVendor case study[1]

Takeaway

BEES expanded candidate discovery while leaving assessment with reviewers.

Categories

Innovation type
Process innovation
AI technology
Generative AI
Evidence
Vendor case study

Sources

Source summaries

[1]Anthropic24 Apr 2024

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.

Added 1 Nov 2026 · Updated 1 Nov 2026
Open case page ↗