2024-08-08: Duo Outages on-going on hour due to Anthropic outtage

Customer Impact

Current Status

More information will be added as we investigate the issue. For customers believed to be affected by this incident, please subscribe to this issue or monitor our status page for further updates.

📝 Summary for CMOC notice / Exec summary:

1. Customer Impact: When users were interacting with Duo chat, they received an error message saying to "try again" as a response couldn't be generated.
2. Service Impact: Category:Duo Chat
3. Impact Duration: 1436 UTC (time of reported incident) - 1600 UTC ( 84 minutes )
   1. NOTE: Anthropic had posted at 2024-08-08 0615 UTC stating some customers experiencing elevated error rates with Claude 3.5 Sonnet so the duration is likely to have been much longer than the 1436 UTC when the incident was initially reported.
4. Root cause: According to Anthropic status page, the underlying issue has now been resolved on their side and all services are fully operational.
   1. NOTE: Though Anthropic is operational, corrective action issues for groupai framework have been created as follow-ups and investigation continues on AI timeouts potentially related to length restrictions. Further updates will come from those issues.

📚 References and helpful links

Recent Events (available internally only):

• Feature Flag Log - Chatops to toggle Feature Flags Documentation
• Infrastructure Configurations
• GCP Events (e.g. host failure)

Deployment Guidance

• Deployments Log | Gitlab.com Latest Updates
• Reach out to Release Managers for S1/S2 incidents to discuss Rollbacks, Hot Patching or speeding up deployments. | Rollback Runbook | Hot Patch Runbook

Use the following links to create related issues to this incident if additional work needs to be completed after it is resolved:

• Corrective action ❙ Infradev
• Incident Review ❙ Infra investigation followup
• Confidential Support contact ❙ QA investigation

---

Note: In some cases we need to redact information from public view. We only do this in a limited number of documented cases. This might include the summary, timeline or any other bits of information, laid out in our handbook page. Any of this confidential data will be in a linked issue, only visible internally. By default, all information we can share, will be public, in accordance to our transparency value.

Security Note: If anything abnormal is found during the course of your investigation, please do not hesitate to contact security.