The Creator of Claude Code Says Prompt Engineering Is No Longer the Main Skill

2026-06-19 · Source: Towards AI - Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

Boris Cherny, creator of Claude Code, a tool used by tens of thousands of engineers daily, recently stated that he no longer directly prompts Claude. Instead, he employs "loops running that prompt Claude and figuring out what to do," shifting his role to writing these loops. This sentiment was echoed by Peter Steinberger, whose post advocating for designing loops to prompt coding agents garnered over five million views. Addy Osmani, an engineering lead at Google Chrome, subsequently named this emerging practice "loop engineering." This development indicates a significant evolution in interacting with AI coding agents, moving beyond manual prompt engineering towards automated, programmatic control.

Key takeaway

For prompt engineers or AI developers building with coding agents, you should prioritize learning "loop engineering" over traditional manual prompting. This shift, highlighted by Boris Cherny and Google's Addy Osmani, means designing systems that programmatically generate and manage prompts for AI. Focus your skill development on creating these automated loops to maximize agent utility and efficiency, as direct prompting is becoming less central to advanced AI interaction.

Key insights

The primary skill for interacting with AI coding agents is evolving from direct prompt engineering to designing automated loops.

Principles

• AI interaction shifts to programmatic control
• Automated prompting supersedes manual prompting

Method

Design and write programmatic loops that generate and manage prompts for AI agents, rather than manually crafting individual prompts.

In practice

• Develop loops to prompt AI coding agents
• Automate prompt generation for Claude Code

Topics

• Prompt Engineering
• Loop Engineering
• AI Agents
• Claude Code
• AI Development
• Automation

Best for: AI Architect, AI Product Manager, AI Engineer, Machine Learning Engineer, Prompt Engineer

Related on AIssential

• Loop Engineering — Design autonomous systems ("loops") to prompt coding agents, replacing direct human interaction for iterative task completion.
• The 6 Claude Code Skills I Would Use for Real Projects — Effective Claude Code skills structure workflows to overcome AI weaknesses, turning repeated prompts into reliable, reusable processes.
• How Claude Code Builds a System Prompt — Advanced AI agents like Claude Code dynamically assemble complex system prompts using numerous conditional components.
• Head of Claude Code: What happens after coding is solved | Boris Cherny — AI agents are rapidly solving coding, transforming software engineering and expanding into general professional tasks.
• 5 Brutally Powerful AI Prompts I Wish I Knew a Year Ago — Effective AI interaction stems from structured prompt design, not just advanced tools or models.
• Prompt Engineering Is Dead. Here’s What Actually Gets AI to Write Good Code. — Effective AI code generation hinges on providing comprehensive context, not just refined prompts.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Towards AI - Medium.