A father of five on running multiple AI agents: delegation is the skill, review is the bottleneck
rschu · x · 2026-09-29
The author argues parents of multiple kids have an unfair advantage with AI agents: years of juggling parallel tasks translate directly into agent orchestration skills.
- Key practices: identify which tasks can run independently (one agent researches, one codes, one drafts) and give each enough context to be useful
- Good delegation becomes a practical AI skill, including knowing when an agent needs clearer instructions
- The bottleneck shifts: five agents finishing at once means five results to review, and an agent saying "done" may deserve the same follow-up as a child claiming to have put their shoes on.
More from coding & agent
- New Dev Consensus: Your SaaS Should Have an MCP Server, Not Just an API — jonathan_wilke · 2026-09-30
- Firecrawl's Alexandria lands in ChatGPT & Codex, claiming 21% better agent answer quality — devdigest · 2026-09-30
- NVIDIA open-sources 3B vision-language model, claims 10x faster grounding than Qwen3-VL — Dan_Jeffries1 · 2026-09-30
- Flatiron School co-founder: AI ends human-first coding, rethink every best practice — kieranklaassen · 2026-09-30
- Skip runtime LLM calls: let Claude generate your no-code automations via MCP instead — Potential-Art7696 · 2026-09-30
- User Woke Up to a 9-Minute Animated Claude-Made Retrospective of Their Work — kevrussell · 2026-09-30