Claude's Microsoft 365 connector down ~20 hours, exposing agent dependency risks
krishnan · x · 2026-11-14
Anthropic's status page shows Claude's Microsoft 365 connector failing most mail, calendar and search requests for roughly 20 hours, taking Claude for Outlook down with it. The root cause was Microsoft's own outage: per Gergely Orosz, it wasn't DNS but networking, and the fix was slow because it required a forward fix — migrating from legacy Exchange to Azure.
The author's takeaway: an agent inherits the uptime of every system it touches. Before handing an agent a workflow, write down what it should do when a dependency is out — wait, degrade, or stop and tell someone.
More from Infra
- Nvidia approaches Arm CEO Rene Haas as potential Jensen Huang successor, per report — AIFlow_ML · 2026-11-14
- Bernstein: Neoclouds earn ~6x more revenue per megawatt than Bitcoin miners — Beth_Kindig · 2026-11-14
- ZONOS3-Mini: MoE TTS model runs realtime on a Pixel 9 and MacBook Air — cocktailpeanut · 2026-11-14
- The Periodic Table of Inference: 12 LLM serving concepts as meme elements — sophiamyang · 2026-11-14
- Open-weights TTS model Tontaube V1.1 runs near real-time on a desktop CPU in 4-bit — EAVDR · 2026-11-14
- MiniMax H3 Image goes live on TensorScale, claimed 2.3x faster and 5x cheaper than fal at 4K — TerryTangYuan · 2026-11-14