Promoting AI agents

David Heinemeier Hansson’s account of changing his mind. He never liked in-editor autocomplete, the format Copilot and Cursor started, because he wants to finish his own sentences. Autonomous agents in a terminal harness feel different to him, less like a pair programmer stealing the keyboard and more like working with a team: they run the tests, search for documentation and use services through skills written in plain English, and he reviews the outcome. The change, he says, is less about the models improving than about giving them tools that take them past pure reasoning.

The promotion in the title is that agents now produce production-grade contributions to real codebases rather than just helping him learn or checking his work. He is careful about how far that goes. Pure vibe coding is still aspirational for professional work; supervised collaboration is what is available today.

He is blunt about the inflated end of the claims:

I’m nowhere close to the claims of having agents write 90%+ of the code, as I see some boast about online. I don’t know what code they’re writing to hit those rates, but that’s way off what I’m able to achieve, if I hold the line on quality and cohesion.

His conclusion is still enthusiastic, calling this the most exciting thing we have made computers do since connecting them to the internet in the nineties, and the advice is to go and try it rather than tune out the hype. No figures beyond the 90% claim he is rejecting.