AAIF Reading Group: A Discussion on Loop Engineering
Loop Engineering: From Prompting to Building Systems That Prompt Themselves
AI development is shifting from manually prompting agents turn-by-turn to engineering autonomous loops: systems that discover work, delegate to agents and sub-agents, verify results, and decide what to do next on their own. It sits one level above harness engineering. A harness equips a single agent run; a loop keeps firing agents, spawning helpers, and feeding itself.
This shift is already tool-agnostic, with Claude Code and OpenAI Codex converging on similar primitives. As Boris Cherny (Head of Claude Code, Anthropic) put it: his job is no longer writing prompts, it's writing the loops that do.
Join David DeStefano, Sam Christensen, Sparsh Jain, Valdimar Eggertsson, and Arthur Coleman for an hour-long open discussion on what they've learned reading into and tinkering with loop-based systems, with plenty of room for audience questions and experiences.
Whether you've worked in the topic or you're simply curious to hear what people are talking about, you're welcome to join: https://home.mlops.community/public/events/a-discussion-on-loop-engineering-me6r7t97sh
🗓 Agenda
👋 Welcome & Introductions (5 min)
📖 Group Discussion (30 min)
💡 Open Discussion & Q&A (20 min)
🎯 Wrap-up (5 min)
👥 Who Should Attend?
AI Engineers
ML Engineers
Software Engineers
Agent Builders
Researchers
Product Managers
Students
Anyone interested in AI agents and autonomous systems
No prior experience with agent frameworks is required, just curiosity.
About AAIF
The Agentic AI Foundation (AAIF) is a community dedicated to advancing the understanding and practical application of agentic AI. We bring together engineers, researchers, founders, builders, and AI enthusiasts to explore how autonomous AI systems are designed, evaluated, and deployed.
Through reading groups, workshops, and community discussions, AAIF brings together engineers, researchers, founders, and AI enthusiasts to exchange ideas, challenge assumptions, and learn from one another.