How to design AI agent loops: schedules, goals, and subagents in Claude Code and Codex
Loops are automated, self-prompting workflows that allow AI agents to perform tasks on a schedule or until a goal is met, reducing manual prompting and enabling scalable automation in software engineering and beyond. The speaker emphasizes that while prompting is still useful, the future
Sign up to read the full summary
Free AI-powered recaps of every episode, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.
Guest
Claire Vo
solo on How I AI
Mentions
Books, people, and resources mentioned in this episode.
People
Products & Tools
Topics
Listen to This Episode
More from How I AI
The Codex feature that works while you sleep
How Intercom 2x’d their engineering velocity in 9 months with Claude Code | Brian Scanlan
How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)
The power user’s guide to Codex: parallelizing workflows, planning techniques, advanced context engineering tips, automating code reviews, and more | Alexander Embiricos
How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)
Claude Code for normal people: skills, voice mode, and how to collaborate with AI
Related episodes
From other shows on similar topics.
Agentic Loops for Knowledge Workers
The AI Daily Brief: Artificial Intelligence News and Analysis
Why humans are AI’s biggest bottleneck (and what’s coming in 2026) | Alexander Embiricos (OpenAI Codex Product Lead)
Lenny's Podcast: Product | Career | Growth
Why the Tech World Is Going Crazy for Claude Code
Odd Lots
We're All Addicted To Claude Code
Y Combinator Startup Podcast
Get summaries like this every morning.
Free AI-powered recaps of How I AI and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.