Multiple agents with different frontier models for best results. Claude code/codex shops don’t know what they’re missing if they never let Gemini roast their designs, code and formal models.
Claude Code wrote a blog article for me documenting a Gemini interaction that I manually operated. I found it quite interesting - the difference in "personalities", and the quality of Claude's output is stark in comparison to the Gemini's.
Bad idea. Use another agent to do automatic review. (And a third agent writing tests.)
Don't forget the architecting and orchestrating agent too!