pretty neat!  Haven't coded in over a decade but I find myself doing something similar for IRL ai prompts: I have a chatgpt and grok tabs pinned and it just takes a quick copy-paste to run queries to both in parallel and sanity check both answers against my own meat-computer to vibe check for consistency and triangulate the truth.

How do you use AI (Agents)?

I was bearish on agents, until I started using them for coding projects. Now I love 'em. 

Decided to write my own framework for agents, [Agro](https://github.com/sutt/agro) to take advantage of something I haven't seen any else do yet: run the same task through all the major coding agents: aider, claude code, gemini cli.

I think my biggest finding is that you can "vibe code" _hundreds of commits on top of each other_ as long as you do QA for each commit. Here's two repos I've been working with, you can see each prompt, and the commits (that were accepted):
- https://github.com/sutt/agro/blob/master/docs/dev-summary-v1.md
- https://github.com/sutt/vidstr/blob/master/docs/dev-log-v1.md

If you'd like to be a beta tester, I can get you some Gemini-2.5-Pro credits gratis. Shoot me a message (contact info in bio)!