One rule for posting agents: never auto-retry a failed publish
petrusenko_max · x · 2026-10-29
The author runs an SMM agent on a Contabo box that posts to X and LinkedIn in a single call. The publish endpoint answers per target, so X can land while LinkedIn errors out — and a blind retry would fix LinkedIn but post twice on X.
His fix: a failed publish immediately ends the run; the agent hands him the text and he posts manually. The takeaway: an agent allowed to post as you needs one button it's only allowed to press once.
More from coding & agent
- Routing coding agents' questions by decision type: 762 questions, only 59 needed the owner — DynoKore · 2026-10-29
- 1.2B tokens later: multi-agent coding run rebuilds a 3D game but hits diminishing returns — teortaxesTex · 2026-10-29
- Unreal Engine runs in the browser via a single Claude agent prompt — chongdashu · 2026-10-29
- Evals and Tracing 101: A Practical Guide for Engineers Building With AI — blaizedsouza · 2026-10-29
- Stop repeating yourself to every AI: a 4-step fix for syncing memory across Claude, ChatGPT and personal agents — jonathanmalkin · 2026-10-29
- hunch: GPU-free ~20ms Jev-like decisions built on EmbeddingGemma 2 — iamrobotbear · 2026-10-29