Why it matters
AI Engineer session on Don't Build Agents, Build Skills Instead, presented by Barry Zhang & Mahesh Murag, Anthropic. It adds practical context for how teams are building and operating AI systems in production.
My takeaway: Don't Build Agents, Build Skills Instead — Barry Zhang & Mahesh Murag, Anthropic 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.