Delegated authority, running locally: Give an agent on your machine an identity you can trust

Part 3 of our agent-identity series: a reference architecture showing how a locally running AI agent, like the coding assistant in your editor or the copilot in your browser, can borrow a human’s authority in a scoped, short-lived, auditable way, anchored in an app the user already trusts. The second post in this series gave us a way to reason about agent identity: a 3x2 taxonomy along two axes. The Authority Model describes the authority under which the agent operates: delegated (acting for a specific human), bounded (operating within a fixed grant), or autonomous (making unsupervised decisio