Claude’s five-hour error window asks how agents recover from model outages
Claude’s June 2 model error incident shows why AI agent products need retry, checkpoint, fallback, and human handoff design.
Claude’s June 2 model error incident shows why AI agent products need retry, checkpoint, fallback, and human handoff design.
Microsoft Scout connects an OpenClaw-style always-on agent to Teams, Outlook, shell, browser, MCP, and Agent 365 controls.
RelationalAI expanded Rel inside Snowflake with a GA prescriptive reasoner, OSI porting, and coding skills for CoCo, Claude Code, Codex, and Copilot.
Asana is packaging Dash, AI Teammates, StackAI, and Command by Asana as an operating system for human-agent teams.
Microsoft tied Aion 1.0 Plan, Edge on-device AI APIs, Windows AI APIs, and MXC into a local agent path for Windows builders.
Sema4.ai introduced Agent Builder, MCP Access Gallery, Business Context Layer, verified queries, and audit logs for enterprise back-office agents.
Google AX is an open source runtime for long-running agents, covering resumption, isolation, auditability, and Kubernetes deployment.
Meta Business Agent now handles customer conversations across WhatsApp, Messenger, and Instagram, changing the competitive terms for BSPs and AI commerce tools.
Microsoft Foundry now ties agent traces, rubric evaluation, optimization, and ROI dashboards into one Agent DevOps loop.
Microsoft Work IQ APIs reach GA on June 16. Here is what M365 context, MCP/A2A, delegated auth, and Copilot Credits mean for agent builders.
Microsoft introduced the early preview of MXC SDK at Build 2026 to isolate AI-agent code, tools, and plugins through Windows and WSL policy.
Tetrate and Ory announced AI agent authorization that can enforce policy on MCP tool-call request parameters, not just tool visibility.