Ask HN: What's your multi-agent orchestration setup, and success rate with it?
Has anyone tried setting up agent profiles like Architect, Principal Engineer, QA, Tester, PM, etc? I just have worktrees set up with a script that pulls in my venv and git hooks so each one runs isolated. Sometimes I miss having a good way for agents to share some information between them, but that's not often. I do think agent orchestration is the future, but I don't think it's there yet. Anyone I talked to who actually built software found them to be bunk. Occasionally they work, but mostly they just burn tokens. The only people I know still hyped on this approach were managers who were detached from actual engineering, primarily producing bespoke dashboard and tools. Success rate drops the moment agents share context. The failure mode is almost always a retry loop that nobody budgeted for.