Developer stops writing prompts — says 'I'm not mad, it's fine' to force agents to ask questions
heyneighbor · x · 2026-09-07
A developer shares a counterintuitive agent technique: instead of carefully crafted prompts, he tells his agents "I'm not mad, it's fine." Deliberately vague, emotionally loaded input forces the agent to probe him with clarifying questions, effectively flipping prompt engineering into letting the agent extract the real task from you.
More from coding & agent
- Dev Builds a Secret Agent Message Board Inside His Personal Linear Team — willcb · 2026-09-07
- Free 155-page Vibe Coding handbook covers specs, tests, deploy: idea to production in 15 chapters — Mahmoud_Zalt · 2026-09-07
- Agent-written Stripe integration caused duplicate charges; sandbox twins fix it — Common_Dream9420 · 2026-09-07
- Qwen Code ships v0.23.1-preview.2 with live subagent status and workflow visualization — qwen-code-ci-bot · 2026-09-07
- The AI engineering methodology ladder: 92% of US devs now vibe coding — No_Stretch433 · 2026-09-07
- APT-RAG Builds Adaptive Reasoning Trees for QA Over Hundreds of Documents — _reachsumit · 2026-09-07