Bob Martin: Don't Build Big Architecture Upfront for AI Agents

mariofilhoml · x · 2026-07-30

Renowned software engineer Bob Martin (Uncle Bob) shared his architectural philosophy for working with AI agents. He stated that he is not a fan of big architecture upfront, preferring to let agents run for a while and adjust the architecture iteratively.

He typically provides only basic hints upfront, such as keeping dependencies pointing from low-level to high-level modules, allowing the architecture to evolve naturally. Furthermore, he believes that if a developer has to manually intervene and inspect the code, it should be viewed as a failure, prompting the need to figure out what went wrong and invent new mechanisms to prevent it in the future.

Original post →

More from coding & agent

coding & agent channel →