Scope Disclosure
Scope disclosure is an AI interface design pattern that presents an explicit, plain-language summary of exactly which resources, accounts, and actions an AI agent can reach, shown at enrollment, surfaced on demand inside the running agent, and reiterated when scope materially changes. This UX pattern replaces the legacy "allow all / deny all" consent modal with a legible contract the user can read, understand, and revisit later. Rather than burying permissions in a Terms-of-Service document, scope disclosure makes the agent's capability boundary a first-class UI surface. The pattern is fundamental to trustworthy agentic products: permissions that are invisible are permissions that silently accumulate, and accumulated permissions are the root cause of most post-hoc security incidents in AI systems.
Use Case
Essential for AI agents, OAuth-based assistants, and any system that acts on behalf of users, where plain-language scope disclosure builds trust and reduces post-hoc security risk.
Examples in Wild
Use this pattern in your project
Copy this prompt to generate a production-ready implementation in Cursor, Claude Code, Lovable, or any AI coding agent.
Generate a production-ready implementation of the "Scope Disclosure" AI interface design pattern.
Pattern Description:Read inbox
Summarize and classify recent email threads.
Send email
Draft and send outbound replies on your behalf.
View calendar
Check availability before scheduling tasks.
Related Patterns
Get new patterns by email
Weekly AI interface UX notes and resources on Substack, no spam, unsubscribe anytime.