We built an org-wide AI agent in 4 days. Here's what broke in the weeks after.
This title could be clearer and more informative.Try out Clickbait Shieldfor free (5 uses left this month).
daily.dev built 'Smith', a 29K-line TypeScript AI agent integrated into their Slack workspace in just 4 days using Codex. The post covers the production incidents and security challenges that followed: credential leaks in a shared runtime requiring a growing command sanitizer, GitHub token bleeding between user sessions, a Node.js event-loop hang that systemd couldn't detect (fixed with a watchdog + health checks), memory exhaustion from a power user's long conversations (fixed with cgroup limits), and a progressive tool disclosure system to manage 60+ tools. Smith self-authors its own reusable skills via a git-backed 'brain' repo and now runs autonomous nightly tasks like spam sweeps and A/B experiment audits. Known remaining issues include an unaudited skill brain, incomplete command sanitizer, and an unsolved crash pattern from one heavy user.
Table of contents
The gap it filled29,000 lines, mostly CodexNot leaking accessThe silent death problemThe teammate who keeps killing SmithProgressive tool disclosureThe brain: 25 skills, all self-authoredWhat it actually does all dayWhat's still broken21 Comments
Sort: