We run a multi-agent pipeline where different AI agents handle different stages: scout, lead, verifier. The system broke when the verifier started trusting the lead's summary instead of doing independent work. The Problem Agent A finishes work and produces a summary: "Fixed the bug.
Source: [Dev.to](https://dev.to/xxxn3m3s1sxxx/your-ai-agents-summary-is-lying-to-you-heres-what-to-do-about-it-4p3h)