tag:status.aurelian.com,2005:/history Aurelian Status - Incident history 2026-09-28T23:59:11.550+00:00 Aurelian tag:status.aurelian.com,2005:Incident/cmulwslui01qp1nqoghk502qb 2026-09-28T23:59:11.550+00:00 2026-09-28T23:59:11.550+00:00 Failure to resolve action items Type: Incident

Duration: 9 minutes

Affected Components: Dashboard

Sep 28, 23:59:11 GMT+0
Identified - We've identified a problem resolving action items that is currently impacting all orgs. This is not impacting calls - Ava is still taking calls and completing them as normal. We are currently working on a fix .

Sep 29, 00:07:44 GMT+0
Resolved - This incident has been resolved. No calls were impacted - dashboard functionality is back to normal .

]]> tag:status.aurelian.com,2005:Incident/cmu3cecrn01un0wocw1n7t278 2026-09-16T00:08:23.045+00:00 2026-09-16T00:16:24.067+00:00 Failure to load overview page Type: Incident

Duration: 8 minutes

Affected Components: Dashboard

Sep 16, 00:16:24 GMT+0
Resolved - This incident has been resolved..

Sep 16, 00:08:23 GMT+0
Investigating - We are currently experiencing an issue loading the overview page for action items. We have identified the issue and are currently working on a fix Call taking is not impacted, you can still view calls in the "Call history" page. .

]]> tag:status.aurelian.com,2005:Incident/cmq8xjc6u05fmqjdpqkwxega0 2026-06-11T00:30:00.000+00:00 2026-06-11T00:30:00.000+00:00 Delays in post task followups Type: Incident

Duration: 2 hours and 14 minutes

Affected Components: Dashboard

Jun 11, 00:30:00 GMT+0
Identified - Post call action items were delayed for a subset of calls, we've fully recovered and post call action items are processing as normal. Delays were occurring between 5:30 and 7:30pm, and a small fraction of action items were delayed by \~20 minutes .

Jun 11, 02:44:25 GMT+0
Resolved - This incident has been resolved. All post call action items are processing as normal. All delayed action items have been posted as expected .

]]> tag:status.aurelian.com,2005:Incident/cmppn7lki009eqqqql4n2h3rb 2026-05-28T14:35:00.000+00:00 2026-05-28T14:35:00.000+00:00 A subset of CORA calls is failing. Type: Incident

Duration: 2 hours and 2 minutes

Affected Components: Cora

May 28, 14:35:00 GMT+0
Investigating - We are currently investigating this incident..

May 28, 15:10:00 GMT+0
Identified - We identified an issue with one of our downstream services that is affecting CORA’s reliability. Approximately 20% of CORA calls are failing. This incident is not impacting AVA calls..

May 28, 16:28:42 GMT+0
Monitoring - Our upstream infrastructure provider has implemented a fix, and our error rate is recovering - we are continuing to monitor. This incident was impacting transcribing call audio for Cora calls, which would prevent the widget from showing. There was no impact to the audio flowing on the calls themselves, and no impact on Ava calls. .

May 28, 16:37:28 GMT+0
Resolved - This incident has been resolved, all Cora services have recovered. Please reach out to us if you continue to experience any issues .

]]> tag:status.aurelian.com,2005:Incident/cmpnoc9ac00zgqmp5lh23fw2t 2026-05-27T00:20:00.000+00:00 2026-05-27T06:15:00.000+00:00 Issue with non-english Ava calls Type: Incident

Duration: 6 hours and 19 minutes

Affected Components: AI Agent

May 27, 06:15:00 GMT+0
Identified - We have identified an issue with non-english calls in Ava that is causing Ava to fail. Calls are being transferred to dispatchers, no call has been dropped. We are currently working on a fix .

May 27, 00:20:00 GMT+0
Investigating - We are currently investigating an issue that appears to be impacting all non-english ava calls. Calls are being transferred to dispatchers, no calls have been dropped. .

May 27, 06:34:17 GMT+0
Monitoring - We implemented a fix and are currently monitoring the result..

May 27, 06:38:52 GMT+0
Resolved - This incident has been resolved..

May 27, 06:39:08 GMT+0
Resolved - The fix has been released, test calls are working as expected. Please reach out to us if you continue to experience any issues .

]]> tag:status.aurelian.com,2005:Incident/cmp001c7w027cpdvbfirla9sq 2026-05-10T16:40:30.666+00:00 2026-05-10T16:40:30.666+00:00 Issue with post-task processing Type: Incident

Duration: 26 minutes

Affected Components: AI Agent

May 10, 16:40:30 GMT+0
Investigating - We are currently investigating this incident..

May 10, 16:41:42 GMT+0
Identified - All agents have been placed into passthrough mode -- all calls are ringing through to dispatch as expected. We are continuing to work on a fix for this incident..

May 10, 16:45:17 GMT+0
Monitoring - We implemented a fix and are currently monitoring the result..

May 10, 16:50:38 GMT+0
Monitoring - Agent is now back on and operational. Will continue monitoring closely. .

May 10, 17:06:26 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.aurelian.com,2005:Incident/cmmywf5280076sxckh4w67hli 2026-03-20T09:15:00.000+00:00 2026-03-20T09:15:00.000+00:00 Delayed Generation of Action Items and Summaries Type: Incident

Duration: 2 hours and 55 minutes

Affected Components: Dashboard

Mar 20, 09:15:00 GMT+0
Investigating - We are currently investigating this incident..

Mar 20, 12:10:00 GMT+0
Resolved - Between 2:15 AM PST and 5:10 AM PST, Aurelian users may have experienced significant delays in action item and summary generation for calls. The internal system causing this has been identified and the issue has now been resolved. Call handling itself was unaffected, and any calls that would normally be handled without an action item were unaffected, including emergency detection, transfers, etc. However, calls that would have generated action items during this time period may not have seen those action items appear until much later. Our team is identifying why internal alerting systems did not identify and alert the issue sooner and working to close any discovered gaps..

]]> tag:status.aurelian.com,2005:Incident/cmlvemjzv03b813qmize7las3 2026-02-20T05:00:00.000+00:00 2026-02-20T05:00:00.000+00:00 Increased Transfer and Error Rates Type: Incident

Duration: 12 hours and 30 minutes

Affected Components: AI Agent

Feb 20, 05:00:00 GMT+0
Investigating - We are currently investigating this incident..

Feb 20, 10:30:00 GMT+0
Resolved - We put up another hotfix to mitigate the issue. .

Feb 20, 06:30:00 GMT+0
Resolved - We put up a hotfix which mitigated the issue. Closely monitoring. .

Feb 20, 09:00:00 GMT+0
Investigating - We started seeing the spike again despite having deployed the hotfix.

Feb 20, 17:30:00 GMT+0
Monitoring - We implemented a fix and are currently monitoring the result..

Feb 20, 15:00:00 GMT+0
Investigating - We started seeing another spike in the transfer rate. .

Feb 20, 16:30:00 GMT+0
Identified - Identified the root cause with one of our providers and started working on the permanent hotfix..

Feb 20, 18:30:00 GMT+0
Resolved - The permanent fix has been deployed..

]]> tag:status.aurelian.com,2005:Incident/cmgzd3g1d03l4mnf23rycw7ju 2025-10-20T16:40:39.195+00:00 2025-10-20T16:40:39.195+00:00 Elevated Carrier Error Rates Type: Incident

Duration: 2 hours and 26 minutes

Affected Components: AI Agent

Oct 20, 16:40:39 GMT+0
Identified - We are observing elevated error rates from Twilio again, which seems to be a continuation of this morning's ongoing AWS outage. We are transferring all calls through to the center out of an abundance of caution..

Oct 20, 18:51:01 GMT+0
Monitoring - We are seeing signs of recovery from Twilio and AWS and are gradually reintroducing traffic to the AI agent..

Oct 20, 19:06:59 GMT+0
Resolved - We are observing broad recovery. We will continue to monitor for regressions from Twilio or AWS' side and update accordingly..

]]> tag:status.aurelian.com,2005:Incident/cmgysubcz02yoyldj0641uwxq 2025-10-20T07:13:40.909+00:00 2025-10-20T07:13:40.909+00:00 Partial Carrier Service Outage Type: Incident

Duration: 2 hours and 36 minutes

Affected Components: AI Agent

Oct 20, 07:13:40 GMT+0
Investigating - We are investigating a potential carrier outage from our carrier partner Twilio. We are actively redirecting all calls directly to the center at this time. .

Oct 20, 07:21:14 GMT+0
Identified - Twilio has confirmed they are experiencing elevated error rates on their APIs. We believe our kill switch should be working as intended and calls should be transferring through to the center. Please text me directly if you are experiencing any active connectivity issues at 908-938-2970 - James.

Oct 20, 08:04:28 GMT+0
Identified - We are continuing to monitor Twilio for updates. It appears there is a major AWS outage that is the source of the issues. We will provide updates as Twilio and AWS make them available. Calls are continuing to be directly passed through to the center..

Oct 20, 09:06:21 GMT+0
Identified - AWS indicates that they have identified the cause and are working on a fix. We are continuing to monitor and will provide additional updates as they become available. Calls are continuing to be redirected directly to the center..

Oct 20, 09:38:01 GMT+0
Monitoring - We are observing significant signs of recovery from AWS and Twilio. We are beginning to route traffic back to our AI and monitoring to ensure full functionality has been restored..

Oct 20, 09:49:11 GMT+0
Resolved - AI Call Handling has been restored to normal functionality. .

]]> tag:status.aurelian.com,2005:Incident/cmdulqgza005xheix1v13gtjb 2025-08-02T17:16:00.000+00:00 2025-08-02T17:16:00.000+00:00 Issues with AI Agent Hearing Callers Type: Incident

Duration: 30 minutes

Affected Components: AI Agent

Aug 2, 17:16:00 GMT+0
Investigating - We are currently investigating this incident..

Aug 2, 17:46:00 GMT+0
Resolved - Summary: From 10:16 PST to 10:46 PST, a subset of calls experienced an issue where Aurelian's AI could not properly "hear" the caller. Our internal systems alerted us to this issue around 10:28 PST and we were able to quickly identify the misbehaving service and recover it. We observed the system fully recover by 10:46 PST. As follow up, Aurelian will review our failover mechanisms to automatically recover from similar events, and will implement failsafes to better detect and transfer callers that this occurs to..

Aug 2, 18:48:31 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.aurelian.com,2005:Incident/cm7lxtuh00032vo1f95xd1cpf 2025-02-26T13:14:54.660+00:00 2025-02-26T13:25:04.112+00:00 Delayed Generation of Action Items and Summaries Type: Incident

Duration: 26 minutes

Affected Components: Dashboard

Feb 26, 13:25:04 GMT+0
Identified - We have identified an issue with an upstream provider and are working to fallback to a backup provider..

Feb 26, 13:14:54 GMT+0
Investigating - We are aware of delayed generation of action items and summaries in Aurelian. We are currently investigating this incident and working on a fix..

Feb 26, 13:32:23 GMT+0
Monitoring - We are seeing signs of recovery and monitoring to ensure all calls are properly processed..

Feb 26, 13:41:24 GMT+0
Resolved - This incident has been resolved. Summary: Beginning at around 5:00 AM PST, action items and summaries for calls handled through Aurelian may have been delayed due to an issue with an upstream provider. Action items may have been delayed by up to 30 minutes. At this time, all action items and summaries should be generating as normal. We will be implementing additional fallbacks to ensure we are not dependent on a single provider moving forward. .

]]> tag:status.aurelian.com,2005:Incident/cm5r5e0p6001c13c2w400q3eg 2025-01-10T04:49:00.000+00:00 2025-01-10T19:59:53.733+00:00 Aurelian Outage Due to Azure Outage Type: Incident

Affected Components: Dashboard, AI Agent

Jan 10, 19:59:53 GMT+0
Resolved - This incident has been resolved..

Jan 10, 06:25:00 GMT+0
Resolved - This incident has been resolved..

Jan 10, 04:49:00 GMT+0
Investigating - We are currently investigating this incident..

]]>