Drawing agent workflows as Feynman diagrams: who decides, what's reversible
_AustinCalvert_ · x · 2026-11-17
smcllns suggests applying the Feynman diagram concept to describing agent workflows and loops, illustrating with a simple Pi Durable email agent. The diagram uses line styles to distinguish decisions made by code, the model, and the human; circles mark reads, diamonds mark reversible world changes, red diamonds irreversible ones, plus notations for temporary trust and sleep states. He wonders how this scales to bigger agentic systems and invites others exploring this to connect.
More from coding & agent
- CUDA guide details fine-grained sync: sentinel-based tile readiness over membar, faster on Rubin — simran_s_arora · 2026-11-17
- Why Lean? Most momentum among dependent type languages, and agents write it decently — hargup13 · 2026-11-17
- Quarterdeck: open-source Claude Code plugin collapses Anthropic's always-on agent stack into one prompt — InternationalData569 · 2026-11-17
- Dev open-sources a local 'room' where coding agents must get human browser approval for risky commands — Significant_Camp4148 · 2026-11-17
- ComfyUI filmmaker solves character consistency with LoRAs, stuck on background — Interesting_Coyote_4 · 2026-11-17
- Amanda Launches API That Sends AI Agents to Meetings for You — Scobleizer · 2026-11-17