Mechanism◆Article · 46:03 — 47:30
Conceptual integrity — the quality where well-designed software has no surprises, covers exactly the right domain, and everything fits together — is much harder to maintain with coding agents because features are added so cheaply.
Referencing The Mythical Man-Month, Simon explains that conceptual integrity — coherence and fit in software design — erodes with agents because the low cost of generating features leads to uncontrolled, incoherent growth. ✦ AI generated
Simon Willison · Simon Willison's Weblog · 2026-08-19 · original ↗
There's a concept in The Mythical Man-Month — conceptual integrity — where well-designed software has an integrity to it: there are no surprises in it, it covers exactly the right domain of things, everything fits together and makes sense. That's so much harder with coding agents, where you can have an idea for a feature, run a prompt, and five minutes later you've got the feature. Your software grows little weird bumps in funny different directions.
Read full article ↗excerpt · fair-use quotation
- ·Conceptual integrity: no surprises, right domain, perfect fit
- ·Crucial for high-quality, coherent software design
- ·Much harder to maintain with coding agents
- ·Agents enable rapid, cheap feature generation
- ·A prompt can yield a feature in 5 minutes
- ·Software grows 'weird bumps' in random directions
- ·Low feature cost leads to uncontrolled, incoherent expansion
- ·Architectural coherence is sacrificed for speed
Around this claim
Context · 2
Lines of code can meaningfully measure productivity because there is a hard ceiling on how much production-ready code a human can write, and coding agents can substantially raise that ceiling.Simon Willison · Simon Willison's Weblog · conf 60%Achieving high-volume, high-quality output from coding agents requires significant skill, knowledge, and experience — the qualities that define senior engineers.Simon Willison · Simon Willison's Weblog · conf 60%