How to design AI agent loops: schedules, goals, and subagents in Claude Code and Codex

Episode notes

I break down every loop type from scratch - what a heartbeat, cron, hook, and goal loop actually are, when each one fits, and the five things any effective loop needs before it touches production. Then I build two live loops: a daily aging-PR reviewer in Claude Code that schedules itself at 10:15 a.m. and spins off its own subagents, and a weekly skills-identification loop in Codex that spawns goal-based subagents to validate its own output in real time.

• Sonnet 5 review: I ran 64 generations to find out if it's worth it53 / 100
• No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)
• GLM 5.2: why I’m replacing Opus in Claude Code with this new model
• How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead
• How Braintrust uses AI agents, evals, and CI to ship better software | Ankur Goyal