Wolfia

Track the health of Wolfia’s Questionnaires, Agent, Trust Center, and API. If something impacts your workflow, we’ll post details and progress here.

Back

Apr 16, 2026

2 months ago

Degraded AI features — upstream Azure OpenAI outage and Claude rate limiting

QuestionnairesAgent

Resolved · April 16 at 10:00 PM (in 45 minutes)

Fully resolved. Total user-facing impact ~45 minutes. Root cause: simultaneous Azure OpenAI regional outage and Claude API rate limiting on our primary provider. Mitigation: we have since expanded our Azure OpenAI footprint from a single region to 7 US regions (westus, westus3, eastus, eastus2, centralus, southcentralus, northcentralus), roughly 5x effective GPT capacity, with automatic health- and rate-limit-aware routing so a localized issue in any one region no longer impacts availability.

Monitoring · April 16 at 9:45 PM (15 minutes earlier)

Azure OpenAI traffic has been routed to a healthy region and Claude requests are succeeding again after backoff. Chat Agent and Questionnaire pipelines are recovering. Monitoring for stability.

Identified · April 16 at 9:15 PM (30 minutes earlier)

We are seeing degraded performance on Chat Agent and Questionnaire answer generation. Upstream cause: an Azure OpenAI regional outage combined with Claude API rate limiting on our primary provider. Engineering is failing traffic over to alternate regions and providers.