Menu

For devs using Claude Code or similar at work: what’s the 10% you still fix by hand in Python?

#code#claude#work#python#photo
Reading 0:00
15s threshold

I keep hearing that AI now writes most of the code at some companies. For people actually shipping Python with Claude Code, Cursor or Copilot:

  1. Roughly what share of your merged code starts as AI output?
  2. What do you most often have to correct? Bugs, tests, pandas or data issues, dependencies, design?
  3. Which skills became more important for you, and which became less important?

Context: I work in risk and data and am deciding what to get good at next. Real examples would help more than opinions. Thanks!