K
Incident Management07:30:48Sun, May 24
Support
Incidents
Active and recent incidents across the platform. All SEV-1/2 events include post-mortems published within 5 business days.
Active incidents
1
MTTA (30d)
3m 12s
MTTR (30d)
42m
Post-mortems posted
8/8
Recent incidents
| ID | Title | Severity | Started | Duration | Impacted | Incident lead | State |
|---|---|---|---|---|---|---|---|
| INC-2026-0428 | Frankfurt inference latency p99 elevated | SEV-2 | 10:42 UTC | 1h 32m | EU tenants · 12 | James Park | Mitigated |
| INC-2026-0427 | PACS sync delay · St Mary's (HL7 backlog) | SEV-3 | 08:14 UTC | 3h 08m | 1 tenant | Maya Singh | Resolved |
| INC-2026-0426 | BrainSeg-MR v3.0.0 rollback (precision regression) | SEV-2 | May 22 18:22 | 42m | All MR tenants | Dr. R. Kapoor | Resolved |
| INC-2026-0425 | Login outage · Okta IdP error 503 | SEV-1 | May 18 14:08 | 18m | All tenants | On-call | Resolved |
| INC-2026-0424 | DICOM router OOM · sg-router-02 | SEV-3 | May 14 02:11 | 1h 04m | APAC | Diego Alvarez | Resolved |
Active incident · INC-2026-0428
Timeline
- 10:42 UTCAlert · p99 inference latency > 1200ms (Frankfurt)
- 10:44 UTCAcked by on-call J. Park · paging SRE
- 10:51 UTCIdentified · GPU node a100-fra-07 thermal throttle
- 11:02 UTCMitigation · drained node, rerouted traffic
- 11:24 UTCLatency restored to baseline · monitoring
- 12:14 UTCStatus: mitigated · root cause in progress
StatusMitigated
Customers notified12 / 12
Status pageUpdated
Slack war room#inc-0428
Post-mortem dueMay 28