The example they were using, however, was Devin, which is supposed to be autonomous. I think they're presenting a slightly different use case than the rest of us are.
I don't believe in the category of "autonomous AI coding agents". That's not how responsible software development works.
If they do bad work their reputation is harmed and they may lose opportunities in the future. They have stakes. They can take responsibility for what they produce.
I believe in AI-assisted development with a skilled human directing the work. That's a huge productivity boost for the humans who learn how to use the tools.
(Twenty years ago people studying computer science in the UK and USA were often told that it was a dead-end career because all of that work was going to be outsourced. That advice aged like stale milk.)
You create a ticket. The AI takes the ticket. The AI may ask questions. The AI creates a pull request. You review it as if it was another coworker.
Most people have not gotten good results from Devin yet. Their business hypothesis seems to be that the models will get good quick and they will have built everything just as the models are good enough to support the model, and will be poised to be first mover.
I suppose their pitch is too eventually go directly to the business and replace the full dev team with this and some technical architects reviewing it but that seems quite optimistic