Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

AI news & research

News ·

Claude login errors take claude.ai and Claude Code down for two hours

Anthropic reported elevated errors and sign-in problems across claude.ai, the Claude Console, Claude Code and Claude Cowork on 13 November. Investigation began at 09:58 UTC, a fix was deployed at 11:05 and the incident was marked resolved at 11:58. No root cause has been published.

For about two hours on Friday morning in Europe, many people could not sign in to Claude. Anthropic's status page shows an incident opened at 09:58 UTC on 13 November for problems authenticating to claude.ai and Claude Code, and closed at 11:58 UTC. If your working day runs through Claude, that is a morning lost, and it was not the only problem that day.

The status record is specific about what broke. Claude.ai was marked as a major outage, the Claude Console at platform.claude.com and Claude Code as partial outages, and Claude Cowork as degraded. The Claude API was not listed among the affected parts. A fix went out at 11:05 UTC, at which point the Console and Claude Code were marked operational again, while claude.ai stayed in major outage until the incident was resolved just under an hour later.

The afternoon brought a second incident. From 13:09 to 15:38 UTC Anthropic reported elevated errors across claude.ai, the Claude API, Claude Code and Cowork, with connectors such as Claude Docs and Claude Sheets degraded for longer. Separately, the Microsoft 365 connector and Claude for Outlook had been failing for most mail, calendar and search requests from 16:03 UTC on 12 November to 16:40 UTC on 13 November, which Anthropic put down to an incident at Microsoft. Overnight, purchases and plan changes on claude.ai also failed for a spell, and on 14 November Sign in with Apple stopped working for some new accounts on the iOS app.

The practical point concerns how you reach Claude. The morning failure sat in the login layer, so tools that call the API with a key, rather than signing in through claude.ai, appear to have been spared until the afternoon errors. Teams that depend on Claude Code for daily work may want an API key or a cloud provider route as a fallback, and a second assistant such as ChatGPT or Gemini for the chat side.

What is missing is an explanation. Anthropic has published no root cause or post-mortem for either 13 November incident, and its updates say little beyond investigating, fix deployed and resolved. Without that, it is impossible to tell whether the two were connected or what has been done to stop a repeat.

Our take: Two hours is short, but teams that now route daily coding through Claude Code felt it, and it is a reminder to keep a second model or tool configured. A public post-mortem would be welcome.

Our reviews:ClaudeClaude CodeClaude Cowork

Source: Hacker News

More stories