I think one way to approach this is by deliberately choosing less capable tools (but still AI-assisted). You don't have to delegate huge tasks to agents wholesale, but it requires fighting against mainstream harnesses to do so because they exist to sell you more tokens. Model providers are not incentivised to offer less autonomous flows.

I wrote about this frustration a few months ago [1], then realised that if the model providers won't do it perhaps I should try fixing it myself. So, shameless plug klaxon, I wrote an open-source harness that tries to work more like pair programming and less like code review [2].

As usual, my "Show HN" post [3] sank like a stone, so I think perhaps most engineers aren't really interested in this direction. It is possible though, we don't have to just accept whatever tooling the labs throw at us.

[1]: https://philbooth.me/blog/agentic-coding-and-mental-models

[2]: https://www.opairdev.org/

[3]: https://news.ycombinator.com/item?id=49625009

▲

eigencoder 3 days ago | parent [-]

Have you tried `pi`? What do you think of it?

	▲	philbo 2 days ago \| parent [-]
		I have. I thought it was okay, but it wasn't really the radical departure from other coding harnesses that I was looking for. Perhaps I could have made it that with more customization, I'm not sure. My own harness doesn't provide the agent with shell access, so everything has to go through focused tools with limited functionality. There's also a navigator mode where the agent has no writable tools at all, instead it monitors the project for changes you make in your regular editor and comments on them in real-time. That stuff seemed easier to implement from the ground up.