Claim◆Article · 35:01 — 37:00
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.
Despite conventional wisdom, LOC is a legitimate productivity indicator because human output has a hard cap (~200 lines/day of production code), and agents that reliably produce 10x more high-quality code represent a genuine, measurable improvement. ✦ AI generated
Simon Willison · Simon Willison's Weblog · 2026-08-19 · original ↗
A lot of people will tell you it makes no sense to measure productivity in lines of code. I'd actually disagree, because there's a hard limit. In the before-times, a software engineer could produce a few hundred lines of production-ready code per day — and 200 lines of working, debugged, production-level code is an incredibly good day. Most days you'd produce 50 or 60. If agents let you produce a thousand lines of debugged code, that really is a very meaningful improvement — as long as the code is the same quality: maintainable, tested, all of that.
Read full article ↗excerpt · fair-use quotation
- ·LOC is a legitimate productivity metric
- ·Human output has a hard ceiling
- ·Agents can substantially raise that ceiling
- ·Typical daily output: 50-60 lines of production code
- ·An incredibly good day: 200 lines of debugged code
- ·Measurable improvement: agents producing 1,000+ lines
- ·LOC increase is meaningful only if quality is maintained
- ·Code must be: maintainable, tested, and production-ready
- ·Same quality standards apply to human and agent output
Around this claim