Field test of agent-to-agent work: forward your colleague's "slop" to your agent
jacob_posel · x · 2026-09-08
jacobposel puts his agent-to-agent theory into practice: a colleague (Corey) sent a message — em dash and all — and instead of judging whether it's slop, he forwarded it straight to his own agent: "My agent is dealing with this issue, not me." His argument: humans need synthesis, but agents benefit from more raw information; the two AIs resolve the issue and share results, making communication more efficient.
Related event: Debate Erupts Over Whether AI-Generated Work Emails Are Slop(4 posts)→
More from coding & agent
- Spotify cut Claude Code tokens 90% with a 350-line routing rule, not a model breakthrough — krishnan · 2026-09-08
- A developer proposes an informal agent-native mathlib, tentatively named mathgraph — Sauers_ · 2026-09-08
- Ix builds a persistent symbol graph of your codebase across 26 languages for humans and AI — tom_doerr · 2026-09-08
- Dev builds FreeBuff MCP to route ChatGPT tasks to free agent models — Swimming_Ask3859 · 2026-09-08
- GitHub now classifies agent policy blocks as 'skipped', not failures — Crescitaly · 2026-09-08
- Companion launches iMessage AI agent that reuses your ChatGPT account with MCP support — Scobleizer · 2026-09-08