When AI Acts Before You Decide 04·09 Compliance used to mean documentation. For AI agents, it means something else entirely 04·08 Microsoft's Argos and the verification layer AI agents actually need 04·07 AI agents fail because they don't know what "customer" means at your company 04·06 Not all AI agents carry the same legal risk 04·02 Agentic AI doesn't need better models — it needs a data constitution 04·01 The vibe coding guy says vibe coding is passé 03·31 AI models that debate themselves are dramatically more accurate 03·30 RAG isn't dead, it just got rebranded as context engineering 03·26 Observational memory changes the AI governance equation 03·25 Get ahead of the skill library problem now 03·24 2026 means stabilizing AI tools, not launching new ones 03·23