Claude Code's Boris Cherny says he stopped writing prompts entirely. Here's what loop engineering means and why it's reshaping AI development in 2026.

Agentic coding needs tighter limits ...

Andrew Ng outlines three key loops for building software with artificial intelligence. The agentic coding loop allows AI ...

One condition did what my nagging couldn't ...

Boris Cherny is the creator of Anthropic’s Claude Code tool, which writes code on behalf of developers based on a text prompt. Cherny hasn’t handwritten code in eight months; instead, he manages ...

Boris Cherny argues that manual prompting is beginning to give way to “loop engineering,” an approach in which AI agents generate prompts and continue working toward a goal with limited human ...

Arbor separates strategy from execution using isolated git worktrees, so engineering teams can finally trace which optimization actually moved the needle.

Loop engineering, a new phrase circulating among AI developers, is becoming a way to describe how software teams are trying to get more value from coding agents: not by writing better one-off prompts, ...

As businesses scramble to rein in soaring AI bills, some are sacrificing polished prose in favor of shorter responses.

As AI agents become more capable, some developers believe the era of carefully crafted prompts is giving way to something more powerful. A growing number of engineers are building automated loops that ...

The loop takes agentic AI a step further, by authorizing a swarm of agents to work continuously in the background, endlessly.