Share via

Azure AI Search Still Experiencing Downtime After Reported Regional Recovery

Dey, Nikita 80 Reputation points
2026-02-03T09:19:11.01+00:00

Hello Microsoft Support Team,

We’re experiencing an ongoing outage with our Azure AI Search service even after the public notification that the West US and East US region issues have been resolved.

Details:

Outage started during the recent West US / East US service failure.

  • The Azure status page shows the incident as "resolved", but our search service remains unreachable / in failed state.
  • We are dependent on AI Search for production workloads and are seeing downtime impacting our applications.

Questions:

  1. Can you confirm whether all Azure Cognitive Search / Azure AI Search resources in West US and East US are fully restored?
  2. Are there any known lingering effects, propagation delays, or backend issues still affecting search services?
  3. Is there an ETA for full recovery or guidance on steps to bring our resource back online?

Please advise on next steps and whether any action is needed from our side.

Thank you.

User's image

Azure AI Search
Azure AI Search

An Azure search service with built-in artificial intelligence capabilities that enrich information to help identify and explore relevant content at scale.

0 comments

Answer accepted by question author

Praneeth Maddali 10,460 Reputation points Microsoft External Staff Moderator
2026-02-03T10:57:34.61+00:00

Hi @Dey, Nikita

Quick summary of what's happening: The root cause was tied to a short-lived Managed Service Identity issue in East US and West US (starting around 00:15 UTC on Feb 3, 2026), plus a related broader VM/service management problem from late Feb 2. The status page now shows no active widespread events for those core issues, and mitigations (like service restarts and traffic ramp-up) have completed with good recovery signals.

That said, services like Azure AI Search (which often depend on managed identities for auth, keys, or backend ops) can have lingering recovery delays—think 30-120 minutes (or occasionally longer) for individual resource partitions/replicas to fully sync and report healthy. This is why the portal might still show "Failed" or "Degraded" even when the platform is stable.

Simple steps to check and help resolve it right now:

  1. Wait and refresh — Give it another 15-30 minutes, then refresh your service overview in the portal. Many cases auto-recover as the backend finishes.
  2. Test directly with API (bypasses portal UI lag): Try a basic query like: GET https://<your-service-name>.search.windows.net/indexes?api-version=2024-07-01 (Use your admin API key in the header.) If this works → the service is actually back online; the status is just lagging.
  3. Check your personalized view — Go to Azure portal > Help + support > Service health. This shows exact impact on your resources (often more accurate than the public status page).
  4. If still stuck — Try a small scale-up/down of replicas (if the operation succeeds) to nudge it, or reply here with your service name + Resource ID so we can escalate to the AI Search team for a targeted check.

Official links for reference:

Please do not forget to click "Accept the answer” and Yes, this can be beneficial to other community members.

If you have any other questions, let me know in the "comments" and I would be happy to help you.

Was this answer helpful?

1 person found this answer helpful.
0 comments

1 additional answer

Sort by: Most helpful
Most helpful Newest Oldest

  1. AI answer

    2026-02-03T09:19:21.2333333+00:00

    It seems that you are experiencing continued issues with your Azure AI Search service despite the reported resolution of the outage in the West US and East US regions. Here are some insights based on the context provided:

    1. Confirmation of Restoration: While the Azure status page indicates that the incident is resolved, it does not guarantee that all resources are fully restored. There can be instances where services may still be experiencing issues even after a public notification.
    2. Lingering Effects: There may be lingering effects or propagation delays that could affect the performance of Azure AI Search services. It is not uncommon for backend issues to persist after an incident is marked as resolved, especially in complex distributed systems.
    3. ETA for Full Recovery: Unfortunately, the context does not provide a specific ETA for full recovery or detailed guidance on steps to bring your resource back online. It is advisable to monitor the Azure status page for updates and consider reaching out directly to Azure support for personalized assistance regarding your specific service instance.

    In the meantime, ensure that your applications are prepared to handle transient faults and consider implementing retry strategies as needed.

    References:

    AI-generated content may be incorrect. Read our transparency notes for more information.

    Was this answer helpful?

    2 people found this answer helpful.

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.