AI agents are breaking the assumption behind traditional authorization models that a caller's needs can be described in advance, according to a comparison of RBAC, ABAC, ReBAC, and the emerging IBAC (…
Google, NVIDIA, Rubrik, Microsoft and Opal have shipped four distinct architectures for AI agent credentials over the past two months, each intervening at a different layer and protecting against diff…
Software engineering is acquiring a "second material" in the form of AI models that carry tolerances — sometimes hallucinating, sometimes not — unlike deterministic code that "always works, or it just…
The Agentic AI Foundation and Linux Foundation Education launched the Model Context Protocol Associate (MCPA) certification on September 14, 2026, the first official vendor-neutral certification for M…
The Model Context Protocol's 2026-07-28 revision removed protocol-level sessions, the initialize handshake, stream resumability, ping, and logging/setLevel, making every request self-contained so any …
WorkOS published a guide on testing AI agent authorization policies before enforcing them, using a reusable YAML test fixture that checks intent, role-based access control (RBAC), and human approvals …
WorkOS published guidance on intent-based access control for AI agents, arguing that the person requesting an agent's work should define its purpose while the organization retains authority over permi…
WorkOS extracted Airlock, its authorization system for governing AI agent actions in company tools, out of its Atlas AI coworker in Slack and into a standalone product, the company said. At Agent Nigh…
WorkOS is offering early access to Airlock, a tool that authorizes specific GitHub merge actions for coding agents while keeping review credentials scoped to Contents: read and Pull requests: write. T…
WorkOS is offering early access to Airlock, an authorization layer that evaluates an MCP agent's declared intent and policy before a tools/call request executes, addressing cases where a valid OAuth s…
WorkOS released Airlock in early access, a tool that requires human approval before a governed AI agent tool call executes and binds that approval to a single request. The workflow stores an immutable…
WorkOS, a developer platform, argues that MCP (Model Context Protocol) and REST are complementary layers rather than competing standards, with most MCP servers internally calling REST APIs. The compan…
WorkOS has launched an MCP server that gives AI agents the same access as a dashboard login, enabling them to manage authentication tasks such as debugging SSO, managing users, adjusting auth policies…
Groupchatty, a tool enabling real-time chat while using Codex and Claude, experienced a sign-in error, preventing users from accessing the service.…
WorkOS has introduced auth.md, an open protocol that standardizes how AI agents register users with apps, modeled after robots.txt. The spec, which composes existing OAuth standards, has been adopted …
WorkOS launched Auth.md, an open protocol for AI agent registration that uses a machine-readable Markdown file at a service root to enable dynamic discovery of OAuth Protected Resource Metadata and se…
WorkOS launched Pipes, a new integration platform that connects AI agents to third-party tools like GitHub, Slack, Salesforce, and Google Drive. The service handles OAuth flows, token refresh, and cre…