@svpino: Many long-held principles and practices translate to the agentic coding era, while many don't. We are all trying to fig…
Summary
The article explores how traditional software engineering principles are evolving in the agentic coding era, emphasizing the experimental adaptation to AI-driven development by software engineers.
View Cached Full Text
Cached at: 09/01/26, 01:45 PM
Many long-held principles and practices translate to the agentic coding era, while many don’t.
We are all trying to figure this out, and pretty much everyone is kinda flying by the seat of their pants.
Software engineers who have embraced agentic coding aren’t “discovering” anything. We are literally finding our way through a completely different and better way to build software.
Daniel Kempner (@DanielKempner): They’re discovering first principles in real time.
Next post: AI agents really seem to prefer descriptively named functions.
Similar Articles
@AndrewYNg: How have software engineering fundamentals changed with agentic coding? Here is our AI Engineering Skills map for softw…
Andrew Ng discusses how agentic coding is changing software engineering fundamentals and introduces an AI Engineering Skills map focusing on key competencies such as full-stack development, data management, and system architecture design.
Vibe coding and agentic engineering are getting closer than I'd like
Simon Willison reflects on how vibe coding and agentic engineering are converging in his own workflow, raising concerns about code review responsibilities as AI coding agents like Claude Code become increasingly reliable. He explores the ethical tension between trusting AI-generated code in production and maintaining software engineering standards.
@Pragmatic_Eng: Old software engineering patterns are coming back because of coding agents. Dax Raad(@thdxr), co-founder of AI coding a…
Dax Raad, co-founder of AI coding agent OpenCode, argues that old software engineering patterns like Domain-Driven Design are becoming relevant again because coding agents, while productive, need more guardrails; the verbosity that made these patterns painful is now handled by AI.
Agentic Coding is a Trap
The article argues that agentic coding, where AI generates code and humans act as orchestrators, is a trap due to increased system complexity, skill atrophy, and vendor lock-in. It highlights the negative impact on developer learning and critical thinking, contrasting this new abstraction with historical programming shifts.
Agentic coding notes from Galapagos Island
Dan Luu reflects on his experiences using AI coding agents, noting that while AI can fabricate convincing but false repros, it still offers productivity gains in areas like debugging and testing. He discusses the balance of trust, automation, and quality in modern software development.