Unified Intent Mediator Protocol
The Unified Intent Mediator (UIM) protocol introduces a standardized approach for AI agents to interact with web services through a unified framework of intents, metadata, and execution methods.
Key components include:
Intents: Structured actions that web services can expose, defining specific tasks such as searching products, placing orders, or retrieving data. Each intent has a unique identifier, metadata, and required parameters.
Policy Adherence Tokens (PATs): Digitally signed tokens issued by web services that encapsulate permissions, billing, and compliance rules, streamlining policy enforcement and automating billing.
Discovery and Execution APIs: AI agents can query discovery APIs to find available intents and use execution APIs to perform actions. Execution involves validation, interaction with the service’s API, response formatting, and error handling.
DNS TXT Records and agents.json Files: Innovative methods for endpoint discovery, allowing AI agents to find and authenticate API endpoints using familiar internet protocols.
Integration with Open Digital Rights Language (ODRL): Provides a structured approach to managing permissions, prohibitions, and obligations, ensuring clear and enforceable rules between AI agents and web services.
Data Licensing Scheme: Define the permissions, conditions, and prohibitions for how data returned by web services can be used according to the UIM Licensing Scheme.
Listen up.
It all begins with an idea… Listen to a deep dive AI-generated conversation about the protocol and its potential.
