Anthropic favicon

Anthropic outage on 2026-11-18

claude.com
November 2026 18 Minor incident

Editing documents through the Google Docs connector on claude.ai, Claude Code and Claude Cowork threw elevated errors for 33 minutes on 18 November 2026. Reading documents was unaffected throughout. Anthropic has confirmed the fault and resolved it on its own status page.

Started

01:13 UTC

Duration

Lasted 33m

Source

IsDown

Next time

Anthropic is degraded. Is your product working?

An incident on their side does not always mean an outage on yours, and the only way to know is to already be watching your own endpoints. Set that up in under a minute and you will be notified the next time your own site is affected. And there will be a next time.

50 monitors for your own websites. No card.

Affected components: claude.ai

What happened?

Anthropic logged one incident on 18 November 2026, starting at 01:13 UTC and running for 33 minutes. The problem was scoped to the Google Docs connector when used for editing documents, across claude.ai, Claude Code and Claude Cowork. Anthropic's first update was explicit that reading documents was not affected, only editing. At 01:40 UTC Anthropic said a fix had been deployed and it was monitoring for recovery. By 01:44 UTC the incident was marked resolved, with Anthropic stating the actual impact window ran from 00:19 UTC to 01:33 UTC on 18 November, which is roughly an hour, a bit longer than the 33 minutes between the first and last updates on the ticket itself. No user reports were filed during the window on this page's record. Anthropic has not published a post-mortem explaining the root cause, so what actually broke in the connector is not on the record beyond "elevated errors". This was one component out of one tracked for Anthropic that day, and it was the only incident logged. Over the trailing 90 days, Anthropic has recorded 47 incidents with a median duration of 1 hour 16 minutes, so this one resolved faster than typical. Across all time, Anthropic averages 29.6 incidents a month, putting this single short connector fault well within its normal rate of disruption.

Learning

This incident sat specifically in the Google Docs connector's editing path, a dependency that lives between Claude and a third party service, not inside Claude's core chat or reasoning functions. If you were watching claude.ai's homepage or basic chat endpoint, your monitoring would have stayed green the entire time, because the fault never touched that surface. It only shows up if you are exercising the connector's write path specifically, which most synthetic checks on your own product don't do by default. That is the general shape of this kind of failure: a scoped integration breaks while the rest of the service answers normally, so uptime on your side tells you nothing about whether a specific feature you depend on is working. Anthropic's own resolution notes are the only record of what happened and for how long, and they don't explain cause. Your monitoring covers your half, UptimeRobot now watches the provider's half too, so next time you know which side broke without guessing.

4.7
stars out of 5
284+ reviews on

Start monitoring in 30 seconds.

There's nothing to install. No credit card required. 50 monitors for free.