AI coding shifts from prompts to loops, making verification the key challenge for engineering teams
By
Arjun Iyer
If you only eat one bagel today, this is the bagel.
Summary
The article discusses a paradigm shift in AI-assisted software development, moving from individual prompt engineering to designing "loops" that autonomously prompt AI agents. This third era of agentic development raises critical challenges around verification, testing, and quality assurance of AI-generated code. The piece explores what this means for engineers' roles, software delivery costs, and the infrastructure needed to support loop-based agentic systems.
Key quotes
· 3 pulledThe argument is no longer about whether agents can write production code or which model is best. It is about who, or what, should be prompting them.
Design loops that prompt your agents.
A third era of agentic development is taking shape, and it raises significant questions about what engineers do, what software delivery costs, and what infrastructure must exist beneath it.
You might also wanna read

AI Software Engineering: Navigating the Paradigm Shift from Assistive Tools to Autonomous Coding
The article discusses the emergence of AI Software Engineering as a transformative force in software development, detailing the evolution fr
The Evolving Role of Software Engineers in the AI Era: From Coding to AI System Architecture
The article discusses the evolving role of software engineers in the age of AI, where traditional coding is being supplemented by AI agent s
How AI Coding Agents Are Fundamentally Changing Software Engineering Practices
The author shares their experience building a product from the ground up using frontier AI models and coding agents, noting a dramatic shift
The Challenge of Verifying Code Quality from AI Coding Agents
The article discusses the author's experience building AI coding agents that work autonomously while they sleep, and the resulting challenge
The Growing Importance of Formal Specification in AI-Driven Software Development
The article discusses the evolving role of software engineers in an AI-driven development landscape, arguing that while initial predictions
How AI agents are shifting developers from writing code to describing problems
The article discusses the emerging workflow where developers describe problems to AI agents that write code, tests, and commit changes auton
