Blog

An API key is one long-lived, over-broad secret. Agent authorization replaces it with a scoped, time-limited, revocable grant tied to a specific user and agent.

Read the full post

One API, three kinds of caller: a person, the app’s own AI, and an external agent. Caller-identity consent lets the data owner consent to each one independently.

Read the full post

A computer-use or prompt-injected agent can click its own Approve if the consent screen sits where it runs. Why that is not proof of a human decision, and the fix.

Read the full post

The Context Access Divide shows why open retrieval matters for AI agents, and why it also needs scoped, user-controlled authorization.

Read the full post

Discovery-by-introspection tells an AI agent what it may do at credential-check time: a scope-filtered map of authorized endpoints with field-level schemas, so a read-only agent never even sees write operations.

Read the full post

A self-describing credential is a token that carries everything an AI agent needs to connect: the agent reads where to exchange it from the token itself, then gets back its scopes, endpoints, and request schemas in one step.

Read the full post

MCP standardizes what an agent can do; it does not give end users per-agent, scoped, revocable control. Add user-mediated authorization so the user approves scopes, the credential goes to the user, and every call is checked against the grant.

Read the full post

User-mediated authorization is a model where the account holder grants an AI agent access directly, and the credential is delivered to the user, not pushed to the agent through an automated channel. Access is scoped, time-limited, and revocable.

Read the full post

To let an AI agent access a user’s account safely, keep the credential off automated app-to-agent channels. Deliver it to the user, scope it to specific actions, time-limit it, and make it revocable. This is user-mediated authorization.

Read the full post