@seclink: Last week, Peter Steinberger wrote about the workflow Boris Cherny adopted at Anthropic: using Claude Code to run looped tasks, such as monitoring Pull Requests (PRs) or scanning GitHub, among others...

X AI KOLs Following News

Summary

Boris Cherny at Anthropic uses Claude Code to run looped tasks, automating workflows like PR monitoring and GitHub scanning, allowing him to orchestrate dozens of tasks from just his phone. Anthropic reports that over 80% of its production code is now written by Claude, showcasing the potential of agentic coding.

Last week, Peter Steinberger wrote about the workflow Boris Cherny adopted at Anthropic: Using Claude Code to run looped tasks, automating work such as monitoring Pull Requests (PRs) or scanning GitHub. Cherny can orchestrate dozens of such tasks in parallel from his phone, merging PRs daily without manually writing code; Meanwhile, Anthropic reported that as of May 2026, over 80% of its production code is written by Claude. Although critics like ThePrimeagen argue this is just a passing trend—citing high token costs and the need for better training—supporters still view it as the future of "agentic coding."
Original Article
View Cached Full Text

Cached at: 06/09/26, 12:50 PM

Peter Steinberger recently published an article detailing Boris Cherny’s workflow at Anthropic:

Using Claude Code for recurring tasks, automating work such as monitoring Pull Requests (PRs) or scanning GitHub.

Cherny orchestrates dozens of these tasks in parallel, using only his phone, without having to write any code manually — enabling him to merge PRs daily.

Meanwhile, Anthropic reports that, as of May 2026, over 80% of its production code is written by Claude.

Although critics like ThePrimeagen dismiss this as a passing fad — citing high token costs and the need for better training — supporters view it as the future of agentic coding.

Similar Articles

@seclink: Developers are shifting from "one-shot prompts" to "agentic loops"—where AI like Anthropic's Claude sets its own goals, uses tools to execute actions, observes results, and iterates until the task succeeds. Boris Chern, developer of Claude Code...

X AI KOLs Following

Developers are moving from one-shot prompts to an 'agentic loop' model, letting AI autonomously set goals and iteratively execute tasks using tools. Claude Code developer Boris Cherny has abandoned traditional IDEs entirely, now running hundreds of agents to monitor issues and merge PRs—even doing so from his phone.

@Huahuazo: Boris Cherny, as head of Claude Code, has long said he doesn't manually write prompts—he writes automated loop programs to drive AI work. OpenClaw's creator has similar practical experience. The community calls this Loop Engineering, upgrading prompt engineering from...

X AI KOLs Timeline

Introduces the open-source project Loop Engineering, which upgrades prompt engineering into building automated loop systems, providing multiple production-grade patterns and tools, and supporting Claude Code, Codex, etc.

@FinanceYF5: Anthropic's Boris Cherny points out that programming is moving towards a higher level of abstraction. A year ago, developers' workflow was to first write code in an IDE, then prompt multiple Claude instances in parallel. Now, the workflow has evolved to writing loops to call Claude, and letting it make autonomous decisions...

X AI KOLs Following

Anthropic's Boris Cherny points out that programming is moving towards a higher level of abstraction, with workflows shifting from manually writing code to letting Claude make autonomous decisions, and predicts that the next paradigm shift will arrive this year.