AI writes 90% of my production code now. Speedup: 3-4x for prototypes, but only 1.5x for prod. The bottleneck moved from writing code to reviewing it. You still have to read every line. Field notes from 6+ months of coding with agents: 1/x
Dec 14, 2025 · 3:39 PM UTC
1
1
74
On quality: A huge share of AI capacity goes to maintaining quality, not adding features. LLM code tends to be over-engineered. Tests it generates are verbose and generic. It's possible to fight that. Good abstractions help the LLM as much as they help you. 2/x
1
1
12
On code review: It's the new bottleneck. Every agent gives you a week's worth of not-great code in hours. You have to review it all. Your team has to review it all. Stacked PRs, better PR hygiene, AI self-review all help. 3/x
1
52
Full post: quality, testing, code review, team dynamics, and what actually changes when agents write your code: open.substack.com/pub/alexan…
41