Why it matters
The LLM in my voice tutor doesn't decide when the lesson is over. It doesn't decide whether the user got the answer right. It doesn't decide which step comes next. A harness does all of that. The LLM just shows up and talks. Every engineer who's tried to ship a multi-step flow agent has felt this: the model declares it
My takeaway: Don't Let the LLM Drive - Ornella Bahidika & Joel Allou, Microsoft is an agent-security signal. The practical read is that autonomy, memory, tool permissions, and third-party integrations are the control surface that needs threat modeling and monitoring.