Dev's take on AI workflows: feed the right data and build verification loops
iamsahaj_xyz · x · 2026-11-16
The author shares how he works with AI: for high-quality initial output, ask the model to gather lots of references and do heavy research up front; to sustain quality, build verification loops so it can check its own work — otherwise agents get lazy.
He suspects this is close to the steady state of working with agents: models will get smarter and more automated, but these fundamentals won't change.
More from coding & agent
- A zero-AI chatbot: 1,000 DeepSeek agents wrote 300,000 if-else rules — victormustar · 2026-11-16
- Open-source Swamp compiles repeated agent skills into workflows: 8x fewer tokens, 2x faster — udmrzn · 2026-11-16
- 67k-star diagram-design skill makes AI coding tools draw editorial-grade diagrams — adnan_hashmi · 2026-11-16
- Every tool is becoming an API for AI agents: a field guide to the agent stack — DEVIL_QI · 2026-11-16
- Alibaba open-sources OpenCodeReview, its internal AI code reviewer using ~1/9 the tokens of Claude Code — udmrzn · 2026-11-16
- Open-source CalDAV MCP Server lets AI assistants manage your iCloud Calendar — Weekly_Mountain2783 · 2026-11-16