Levity AI Outage History
5 incidents recorded over the last 365 days, 5 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 Levity AI Incident
| Date | Incident | Duration | Status |
|---|---|---|---|
| Aug 24, 2026 | Delay in flow executionsThe configuration was updated. Execution is back to normal | -23 min | Resolved |
| Jul 16, 2026 | Login unavailable due to authentication provider (WorkOS) outageWorkOS has resolved the incident on their platform (12:44 CEST, see status.workos.com) and we have verified that logging in to the Levity web app works normally again. Running flows and automations were not affected at… | 2h 4m | Resolved |
| Mar 27, 2026 | Gemini model Ai Blocks intermitenceIssue has been supressed with fallback models. No more errors showing up since 16:58 GMT. | -20 min | Resolved |
| Nov 21, 2025 | Temporary issue affecting classification resultsA temporary issue in our classification logic caused some results to be missed in certain flows. The issue was identified and fixed. | -1581 min | Resolved |
| Nov 6, 2025 | Security Update Deployed - All Users Logged OutAt 1:40 PM CET, we completed a planned security update. This update logged all users out as a one-time security measure. This was expected behavior. Users can now log back in normally. The platform is fully operational. | -1 min | 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 Levity AI 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 Levity AI 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 Levity AI 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 Levity AI outage in this window ran 2h 4m, against a mean recovery of 2h 4m. If you depend on Levity AI 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.