I have more than a few side projects that began as late night discussions with an llm. A couple of those projects reached a level of completion where I use the products daily, and one project reached production (a game you can find referenced on my profile).

I have had similar experiences to the author, and I’ve found that just working with a single agent in Antigravity (on the Gemini Pro subscription) is adequate. The extra perceived speed and power of multiple agents and/or Claude Code really didn’t match the output.

With a single Gemini (or sometimes switching to Claude Opus which inexplicably Google provides a generous amount of for free via AG) gives me incremental results so fast that I spend most of my time thinking about what I want (answering unplanned product questions or deciding how to handle edge cases).

I’m fact, sometimes I just get exhausted with so much decision making. However, that’s what it takes to build something useful; we just aren’t accustomed to iterating so fast!