Design, specify, map, evaluate, or improve an AI assistant, LLM feature, copilot, chatbot, agent, recommendation, generation, or automation workflow. Define capability boundaries, user control, recovery, trust, evidence, uncertainty, permissions, and evaluation. Trigger on "design this AI feature", "build an AI feature", "chatbot design", "improve this copilot", "AI automation", or "plan this agent workflow". Do not use for model training or prompt-only writing.