Key Points

The quote argues that agentic coding can be inefficient over the long run because agents may brute-force solutions and waste substantial compute (e.g., enormous token use) rather than producing maintainable results.
It advocates designing AI agents and systems to solve tasks quickly while remaining maintainable, adaptive, and composable with improvements from the broader ecosystem.
The proposed approach emphasizes strong foundational libraries with well-designed interfaces, so the “right” way becomes the easy way for developers building on top of them.
The overall message reframes developer focus from writing lots of code to thinking more deeply about architecture as AI assistance increases.
The post is presented as a curated quotation (not a new technical release), highlighting a conceptual view of how to build agentic coding workflows responsibly.

Simon Willison’s Weblog

Sponsored by: WorkOS — Ready to sell to Enterprise clients? Build and ship securely with WorkOS.

28th March 2026

The thing about agentic coding is that agents grind problems into dust. Give an agent a problem and a while loop and - long term - it’ll solve that problem even if it means burning a trillion tokens and re-writing down to the silicon. [...]

But we want AI agents to solve coding problems quickly and in a way that is maintainable and adaptive and composable (benefiting from improvements elsewhere), and where every addition makes the whole stack better.

So at the bottom is really great libraries that encapsulate hard problems, with great interfaces that make the “right” way the easy way for developers building apps with them. Architecture!

While I’m vibing (I call it vibing now, not coding and not vibe coding) while I’m vibing, I am looking at lines of code less than ever before, and thinking about architecture more than ever before.

— Matt Webb, An appreciation for (technical) architecture

Posted 28th March 2026 at 12:04 pm