AI coding tools are optimising the wrong thing and nobody wants to hear it. Writing code was already fast. The bottleneck is everything else: unclear requirements, review queues, terrified deploy cultures, and an org chart that needs six meetings to decide what colour the button should be.
All code is written quickly these days, and not by humans. The patterns to guard against bugs also help speed development, and are the same we already learned.
I’ve found the biggest bottleneck is bugs. If you catch a bug during development, it takes the least time to fix.
Catch a bug during PR, you need to fix the code, and the PR needs to happen again.
Catch a bug in QA, and you need to fix the code, do another PR, and get it tested again.
This pattern goes right through UAT, and god help you when a bug makes it to Prod.
There is nothing more time consuming than code that was written quickly.
All code is written quickly these days, and not by humans. The patterns to guard against bugs also help speed development, and are the same we already learned.
Strong typing and test driven development.
Quality is speed.
Slow is smooth. Smooth is fast.
Or by word processors.