# Loop Engineering Went Mainstream Mid-2026, and "loop engineering" is now the phrase you keep seeing in AI conversations. Boris Cherny from Claude Code said it directly: "I don't prompt Claude anymore. My job is to create loops." Jensen Huang said something nearly identical. So is this a real shift or just a rebrand? I think it's both. The critics have a point: the concept of agent loops is not new. ReAct dates to 2022, Reflexion to 2023. What Willison described as "something that runs tools in a loop to achieve a goal" has been the working definition for years. If your reaction to "loop engineering" is "isn't this just agentic design with a new name," you are not wrong. But the rebranding reflects something real. The bottleneck actually moved. METR's data is concrete: Claude Opus 4.6 now completes 50% of tasks that take ~12 hours, up from ~1h40 a year earlier. Models can now run long enough and recover reliably enough that the constraint is no longer the model. It's the harness. It's the loop design. The Terminal-Bench 2.0 results make this vivid: the same model swings 30-50 percentage points depending on which harness runs it. That is not a marginal difference. That is the actual claim behind the label. The high-leverage skill moved. Prompt engineering still matters; context engineering still matters. But the system that runs the prompts now matters more. If you are spending most of your AI time crafting individual prompts and almost no time thinking about triggers, verifiers, stopping conditions, and sandboxing, you are optimizing the wrong layer. Keep in mind: loops only pay off with a deterministic validation gate. Without one, an agent agreeing with itself on repeat is not autonomous work. And if human review is already your bottleneck, adding a loop just floods the queue. The productivity gains are real, but they require designing the harness first, not bolting it on after. I have been tracking this through [[Agentic loops]], [[Harness Engineering]], and [[AI Agent Harnesses (MoC)]] for a while now. The pattern is consistent: the builders who get reliable results from agents are the ones who treat loop design as a first-class engineering problem, not a prompt-quality problem. The label may be new. The lesson is not: design the system, not just the message. ## References - Simon Willison, "Designing agentic loops" (2025-09-30) — https://simonwillison.net/2025/Sep/30/designing-agentic-loops/ - Anthropic, "Effective harnesses for long-running agents" — https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents - bdtechtalks, "Demystifying loop engineering" (2026-06-22) — https://bdtechtalks.com/2026/06/22/ai-loop-engineering/ - Data Science Dojo, "Agentic Loops: From ReAct to Loop Engineering (2026 Guide)" — https://datasciencedojo.com/blog/agentic-loops-explained-from-react-to-loop-engineering-2026-guide/ - HN: "Designing agentic loops" — https://news.ycombinator.com/item?id=45426680 - Paweł Huryn on X (Cherny / Huang quotes) — https://x.com/PawelHuryn/status/2069315068664197315