AI Agents Need a New Identity Model

Twenty years of authentication rules are dead. AI agents act autonomously but carry human authority, and no existing credential model handles both cleanly. This episode breaks down the four essential questions: should an agent authenticate as the user or itself? How do you delegate authority for services discovered mid-task? What replaces long-lived API keys? And what architecture survives as the boundary between user and software dissolves? We explore composite identity, just-in-time scope discovery, and the credential issuance patterns that are replacing static secrets. Episode #325214 — open it directly at myweirdprompts.com/325214