Herding AI Cats: Developer Shares Pain Points of Multi-Agent Workflows
DanWahlin · x · 2026-08-05
Veteran developer Dan Wahlin shared his real-world experience collaborating across multiple projects using various AI coding tools, including Hermes, Copilot CLI, Claude Code, Codex, and Grok Build.
He noted that even with a great process in place, hopping between agents while maintaining human-in-the-loop reviews is draining. He compared the experience to having multiple people stopping by his office all day asking, "Do you have a few minutes to chat?", describing the management of these AI tools as "herding AI coding cats."
More from coding & agent
- npm Responds to Security Incident by Rotating Tokens and Pushing OIDC Publishing — RSync25 · 2026-08-05
- Linux Staging Area Now Rejects LLM-Generated Patches Except Security Fixes — edparadox · 2026-08-05
- Configuring Claude Code: Using Simplified Technical English Globally — mattpocockuk · 2026-08-05
- Unexpected Codex Use Case: Plugging In Your Phone to Automate UI and File Management — Yamapama · 2026-08-05
- GitHub Copilot CLI Update Introduces Breaking Change in Sandbox Settings — copilot-cli-release-app[bot] · 2026-08-05
- Coding Agent Pain Points: Directly Manipulate Real State, Not Just Code — mmmbchang · 2026-08-05