Glean Outage History
7 incidents recorded over the last 365 days, 7 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.
Every Recorded Glean Incident
| Date | Incident | Duration | Status |
|---|---|---|---|
| Oct 26, 2026 | We are investigating elevated Server errors affecting Claude model requests through AWS BedrockWe are investigating elevated Server errors affecting Claude model requests through AWS Bedrock. We will share updates as more information becomes available. | 2h 4m | Resolved |
| Oct 22, 2026 | We are investigating an issue impacting AWS customers using Sonnet 5.5 through BedrockWe are investigating elevated Server errors affecting Claude Sonnet 5.5 requests through AWS Bedrock. We will share updates as more information becomes available. | 1h 43m | Resolved |
| Oct 12, 2026 | AWS Bedrock rate limiting for Claude OpusHTTP 429 rate-limit errors from AWS Bedrock remain unresolved. We are initiating failover of all affected customers to an alternate provider as a mitigation. We will share another update as the failover progresses. | 8h 45m | Resolved |
| Sep 3, 2026 | AWS issue appears to be resolved; monitoringThe intermittent issue affecting AWS credential refreshes appears to be resolved. Error rates in our backend systems have subsided, and we’ll continue to monitor closely. | 1h 59m | Resolved |
| Sep 1, 2026 | We are investigating an issue impacting Chat/AssistantWe have identified an internal regression that is causing chat/assistant requests to fail.The root cause has been identified and we are rolling out a fix soon. | 3h 5m | Resolved |
| Aug 31, 2026 | We are investigating an issue impacting Glean assistantAzure OpenAI has acknowledged an ongoing outage and is actively working to resolve it. As a workaround, BYOK customers can configure their default model to use a provider other than Azure OpenAI from the LLM settings… | 2h 57m | Resolved |
| Aug 24, 2026 | Customers on Glean Key and using OpenAI models are facing rate limits causing chat failuresWe are hitting Open AI rate limits due to organic traffic growth. We are closely working with Open AI team to fix this. | 1h 38m | Resolved |
Hear about the next one while it is open
Everything above is a record written after the fact. We can email you when the next Glean incident opens instead, at the point where knowing still changes what you do.
Free, no password, no card. Unsubscribe in one click.
How to Read This Glean Incident Log
Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before Glean acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.
Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.
The longest single Glean outage in this window ran 8h 45m, against a mean recovery of 3h 10m. If you depend on Glean in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.