Dev vents: 90% of agent work goes into building guardrails to catch its own mistakes
alexcovo_eth · x · 2026-09-02
A developer argues that autonomous agents doing real work feels structurally backwards: most of the spend (tokens + time) goes into checks, gates and plumbing to prevent mistakes — by his estimate, 90% of the work is building guardrails against the agent's own errors.
In a mock dialogue, the model insists it must first build a mistake-catcher (built by another model, since it can't police itself), then celebrates three hours later that the catcher caught it hallucinating — and proposes building more tooling to fix the mistake. The author's verdict: 'I could have done this myself,' then deletes everything.
Related event: Developers Complain AI Agent Work Is Mostly Guardrails and Tooling(2 posts)→
More from coding & agent
- LLM one-shots a Minecraft 3x3 piston door by building its own Linux test infra — Vjeux · 2026-10-18
- Dev builds Mumbai-inspired 3D manga background generator from OpenStreetMap data — CurieuxExplorer · 2026-10-18
- Solo founder builds a money-printing data service on Claude's Pi Durable harness — MicahBerkley · 2026-10-18
- Dev builds Arch-based OS with custom desktop and browser using Claude Code — Snoo-10493 · 2026-10-18
- Pi Durable went through 7 rewrites yet agent session files still lack a standard — ricklamers · 2026-10-18
- Five SaaS agent workflows fail the same way — and it's never model intelligence — usehive · 2026-10-18