Nothing about this feels inflexible to me at the moment - I'm evolving the way I use these tools on a daily basis, constantly discovering new tricks that work.

Just this morning I found out that I can tell Claude Code how to use my shot-scraper CLI tool to debug JavaScript and it will start doing exactly that:

  you can run javascript against the page using:
  shot-scraper javascript /tmp/output.html \
  'document.body.innerHTML.slice(0, 100)'
  - try that

We don't need automation for that, we "achieve" that through our processes already. Specifically, software creation processes of large teams with many changing developers over long periods. Example (but they are not the only one): https://news.ycombinator.com/item?id=18442941 -- changing or adding anything becomes increasingly burdensome.

I would like to post that every time somebody warns of the dangers of AI for maintainability. We are long past that point, long before AI. Businesses made the conscious decision that it is okay for quality to deteriorate, they'll squeeze profits from it for as long as possible and then they assume something new has already come along anyway. The few business still relying in that technical-debt-heavy product are still offered service, for large fees.

AI is just more of the same. When it becomes too hard to maintain they'll just create a new software product. Pretty much like other things in the material world work too, e.g. housing, or gadgets, or fashion. AI actually supports this even more, if new software can be created faster than old code can be maintained that's quite alright for the money-making oriented people. It is harder to sell maintenance than something new at least once every decade anyway.