Prompting agents without touching code is basically engineering management, he says
irvinebroque · x · 2026-07-24
- The thread responds to a debate about prompting agents without directly reading or editing code.
- The core argument is that the skills involved look a lot like engineering management: setting constraints, identifying problems, giving feedback, creating loops, and going deep when needed.
- The post emphasizes that the frustration around this debate reflects how hard good engineering management is in practice.
More from coding & agent
- Coco adopts GUM proposition-evidence memory for better in-memory search — EchoShao8899 · 2026-07-24
- A small agent-name joke lands inside the AI community — huangyun_122 · 2026-07-24
- Open-source package normalizes coding-agent sessions into one standard trajectory format — carsonfarmer · 2026-07-24
- Vercel lets Workflows pin state to a region, with AI Gateway limits coming soon — cramforce · 2026-07-24
- ChatGPT Voice tips warn users to offload work into new threads and expect context resets — jxnlco · 2026-07-24
- 30 open-source AI repos covering agents, local inference, and workflow automation — Shruti_0810 · 2026-07-24