Don't One-Shot Big Tasks: Split Work Into Small Agent Sessions, Then Orchestrate
koltregaskes · x · 2026-08-26
The author shares practical advice for working with AI agents: never hand them one huge, complicated task — they still struggle with very large jobs.
- Break work into small pieces, run 2-4 sessions in parallel, then use a new session to orchestrate and assemble the parts once they've progressed
- Only some agents (e.g., ChatGPT and Claude) can currently orchestrate other sessions; you can also start with the orchestrator and have it spawn sub-sessions, but the plan must be tight
- Another trick: have the agent work in "chunks," pausing to prompt you before moving on — great for long outputs from a single task and better use of context space
More from coding & agent
- Grok Bot books haircut autonomously: seamless payment via Stripe — mattshumer_ · 2026-08-26
- 3D game prototype built with Codex: Milo's clock adventure — techartist_ · 2026-08-26
- Dev Tip: Start with wireframes, even when coding directly — floguo · 2026-08-26
- Dev Diary: Managing multiple AI agents is the new bottleneck — therealdanvega · 2026-08-26
- LangSmith Engine upgrade boosts agent issue detection by 2x — LangChain · 2026-08-26
- Paperclip indexes 170M patents to enhance AI agent scientific retrieval — james_y_zou · 2026-08-26