https://www.infoq.com InfoQ Zero Trust News feed https://www.infoq.com/news/2026/06/ai-agent-identity-uber-auth0/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Zero+Trust-news <img src="https://res.infoq.com/news/2026/06/ai-agent-identity-uber-auth0/en/headerimage/Auth0-Header-1781600533444.jpeg"/><p>Uber recently described an internal architecture for propagating identity across multi-agent AI workflows. The design aims to perserve user context, agent provenance, and scoped access as agents delegate work and call internal tools. The case study aligns with Auth0’s view that AI agents need permissions based on delegated authority, scoped credentials, and explicit human approval boundaries.</p> <i>By Eran Stiller</i> Model Context Protocol (MCP) OAuth Agents Zero Trust Architecture Identity Management AI Security Agent2Agent Development Architecture & Design news Wed, 17 Jun 2026 12:15:00 GMT https://www.infoq.com/news/2026/06/ai-agent-identity-uber-auth0/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Zero+Trust-news Eran Stiller 2026-06-17T12:15:00Z /news/2026/06/ai-agent-identity-uber-auth0/en