Running three agents(gpt, gemini, claude) in production for a different domain — curious which model handles the /studio skill best in your experience?
The reactive execution model as agent memory is clever — I ran into similar tradeoffs building a multi-agent trading system where each agent needs isolated state across cycles. Ended up using a persistent store (BigQuery) rather than in-process memory, but the appeal of having the runtime itself be the memory is that you get reproducibility for free.