Unlocking Swarm Intelligence with Big Agentic Brain and Claude Code

说明与用途

Big Agentic Brain（BAB）让代理共享关于需要团队知识的错误的知识，将成功修复率提升至100%，并将修复成本降低一半。

问题

AI coding agents lack shared team knowledge, causing low success on bugs that depend on vendor quirks or runbook conventions.

结果

BAB increased team‑knowledge bug fix rates from 12%–0% to 75%–100%, improved teammate fix rates from 13%–67% to 96%–100%, and halved cost per verified fix for Haiku.

工作流

• 1. Agent searches BAB before starting.
• 2. Agent solves bug and records fix, vendor quirk, or convention as a structured entry.
• 3. Agent reacts to other entries, influencing ranking.
• 4. Teammate agents retrieve shared entries via MCP and apply them to related bugs.

证据

Sonnet went from 12% to 79% with BAB, and to 100% (24/24) with a one-line search-first nudge.

来源

With shared BAB, teammates fixed the bug 96 to 100% of the time, against 13 to 67% with local notes only.

来源

For Haiku it was about half the no-memory cost.

来源