Loop Engineering
You don't really need to be good at prompting anymore. The thing to get good at is the loop that does the prompting for you. It's five building blocks plus s...
Loop engineering is replacing yourself as the person who prompts the agent. You design the system that does it instead. A loop here can be thought of a recursive goal where you define a purpose and the AI iterates until complete. I believe this may be the future of how we work with coding agents. However, its still early, I’m skeptical and you absolutely have to be careful about token costs (usage patterns can vary wildly if you are token rich or poor), so I want to unpack what it is and what it means. Peter Steinberger recently said: “You shouldn’t be prompting coding agents anymore. You…
saved by
related reading
- The Coming Loop | Armin Ronacher's Thoughts and Writingslucumr.pocoo.org
- Designing agentic loopssimonwillison.net
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- claude code is not making your product betterethanding.substack.com
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- The Unreasonable Effectiveness of Agentic Loopsweb.navan.dev
- Building Effective AI Agents \ Anthropicanthropic.com
- Welcome to Learn Harness Engineeringwalkinglabs.github.io
- Ampampcode.com
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Harness design for long-running application developmentanthropic.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com