What AI development has done for my team is the following:
Dramatically improved Jira usage -- better, more descriptive tickets with actionable user stories and clearly expressed requirements.
Dramatically improved github PRs.
Dramatically improved test coverage.
Dramatically improved documentation, not just in code but in comments.
Basically all _for free_, while at the same time probably doubling or tripling our pace at closing issues, including some issues in our backlog that had lingered for months because they were annoying and nobody felt like working on them, but were easy for claude to knock out.
I'd be willing to bet that your AI written issues, docs, etc look impressive initially but are extremely low signal to noise. You might be checking some boxes (docstrings, etc) but I do not envy anyone on your team that needs to actually read any of that stuff in the future to solve an actual problem.
I keep describing this as the environmental protection meme, "but what if we make the world a better place - for nothing!"
Even if AI goes away tomorrow, we'll still have better tooling, documentation and processes just because we HAD to implement them to use AIs more efficiently.
> Dramatically improved Jira usage -- better, more descriptive tickets with actionable user stories and clearly expressed requirements. Dramatically improved github PRs. Dramatically improved test coverage. Dramatically improved documentation, not just in code but in comments.
> Basically all _for free_
Not for free, the cost is that all of those are now written by AI so not really vetted any longer. Or do you really think your team is just using AI for code?
Dramatically improved Jira usage -- better, more descriptive tickets with actionable user stories and clearly expressed requirements. Dramatically improved github PRs. Dramatically improved test coverage. Dramatically improved documentation, not just in code but in comments.
Basically all _for free_, while at the same time probably doubling or tripling our pace at closing issues, including some issues in our backlog that had lingered for months because they were annoying and nobody felt like working on them, but were easy for claude to knock out.