Elevated errors on Claude Code and Claude Cowork

What to do

• Check whether you use Anthropic Claude Code, Claude Cowork. Check your stack

  Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.

• Confirm your retries, queues and scheduled jobs caught up after the 2h 59m it lasted.

  Anything that failed between 2026-08-28 17:22 UTC and 2026-08-28 20:21 UTC may need a replay.

• Subscribe to Anthropic's feed to hear about the next one first. RSS feed

  https://down.guide/feed?provider=anthropic works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from Anthropic 3

1. identifiedAug 28, 2026, 5:22 PM UTC

   We have identified an issue with an upstream cloud provider affecting Claude Cowork and Claude Code on the web. Some sessions may fail to start or disconnect mid-task; affected sessions can be retried. We are in contact with the provider and will provide an update as soon as possible.

   provider

2. monitoringAug 28, 2026, 6:21 PM UTC

   A mitigation has been applied for the issue affecting Claude Cowork and Claude Code on the web, and we are monitoring for recovery. Sessions that disconnected earlier can be retried

   provider

3. resolvedAug 28, 2026, 8:21 PM UTC

   The issue affecting Claude Cowork and Claude Code on the web has been resolved.

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.