Agent Permissions

Agent permissions define what an AI agent is allowed to read, edit, create, publish, or automate inside a project.

Agent permissions help teams control risk when using AI. A project may allow an agent to edit CMS content, inspect pages, or create branches, while reserving publishing, production changes, or destructive edits for human approval.

Related terms

Related terms

  • Sandbox

    AI

    A Sandbox is a constrained runtime environment that limits file, network, or system access to reduce risk during automated execution.

  • Approval Modes

    AI

    Approval Modes are policy settings that control which operations an agent can run automatically and which require explicit human approval.

  • Agent Workflow

    AI

    An agent workflow is a sequence of AI-assisted steps for planning, editing, reviewing, and shipping work in a digital project.

    An agent workflow breaks complex website work into smaller actions such as scanning pages, updating CMS items, improving layout, and reviewing changes. Clear workflows help teams use AI without giving up control over quality or publishing decisions.

  • Agent Branch

    AI

    An agent branch is a separate working version of a project where AI-made changes can be reviewed before they affect the main site.

    An agent branch protects the live project by isolating AI edits. Teams can preview the result, compare changes, request revisions, and merge only when the work is ready.

  • Team workspaces

    Framer

    In Framer, team workspaces give groups a shared place to manage sites, collaborate on designs, and keep ownership clear across projects.

  • Invite links

    Framer

    In Framer, invite links simplify collaboration by letting the right people join a project quickly while permissions and roles keep access manageable.

  • SSO

    Framer

    In Framer, SSO supports larger teams by connecting authentication to company identity systems, simplifying onboarding, permissions, and account security.