MSFT take on Agents 05·02 MCP registries aren't catalogs — they're control planes 04·30 Harness Engineering: Why Better Models Aren't Enough to Ship AI Agents 04·29 You actually cant see your agents 04·28 Agents make retrieval harder, not obsolete 04·27 What a Lisbon cafe told me about Anthropic's marketplace experiment 04·26 Onyx security raises $40M to build an AI control plane for enterprise agents 04·23 EUDI Wallets could be the trust layer agentic AI needs — but the law hasn't caught up yet 04·22 AI agents could dissolve the friction that keeps justice expensive 04·21 What Andrej Karpathy and your legal team both get right about vibe coding 04·20 When engineers define "AI-ready," legal inherits the error 04·16 Agent Governance Toolkit: what it is and why runtime enforcement is the missing layer 04·15