Pencil Outage History

26 incidents recorded over the last 365 days, 20 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.

Live Pencil status100.00% uptime history

Every Recorded Pencil Incident

Pencil incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Aug 16, 2026Queue Cluster maintenanceThe scheduled maintenance has been completed.25 minScheduled
Aug 16, 2026Scheduled Message Queue MaintenanceScheduled maintenance is currently in progress. We will provide updates as necessary.25 minScheduled
Aug 3, 2026Login Issue on app.trypencil.comThis incident has been resolved.18 minResolved
Jul 21, 2026Scheduled maintenanceThe scheduled maintenance has been completed.10 minScheduled
Jun 10, 2026Third-Party Tool IssuesThis incident has been resolved.37 minResolved
Jun 4, 2026Rate limit issues with the following models:This incident has been resolved.120h 13mResolved
May 28, 2026Workflow Feature IncidentEarlier today, we had a faulty release that caused issues with the Workflow feature. As a result, some workflow executions were not functioning as expected. The issue has now been identified and fixed, and the feature…-74 minResolved
May 27, 2026Temporary Service Degradation — Kling ModelThis incident has been resolved.1004h 12mResolved
May 25, 20263P Agent Tool Connectivity IssuesThis incident has been resolved.22h 43mResolved
May 8, 2026Investigating Queue Cluster Network SpikeThis incident has been resolved.1h 24mResolved
Apr 28, 2026Ongoing Issue with Sora 2 and Sora ProThis incident has been resolved.21h 31mResolved
Apr 25, 2026Ongoing Platform Upgrade – Possible DisruptionsThe scheduled maintenance has been completed.2h 30mScheduled
Apr 16, 2026Elevated Error Rate on Runway Models:This incident has been resolved.24h 27mResolved
Apr 16, 2026Incident UpdateThis incident has been resolved.1h 34mResolved
Mar 31, 2026Increased Error Rates for Nano Banana ProThis incident has been resolved.29h 13mResolved
Mar 18, 2026Resource Exhaustion Errors on Google AI ModelsThis incident has been resolved.269h 41mResolved
Mar 9, 2026RabbitMQ Cluster Network PartitionEarlier today, our RabbitMQ cluster experienced a network partition, which caused temporary instability in the messaging system. During this time, there was a risk of delayed or unprocessed messages. Our team…-136 minResolved
Mar 6, 2026Elevated Error Rates for Nano Banana ModelThis incident has been resolved.15h 48mResolved
Feb 27, 2026Resource Exhaustion Errors on Google AI ModelsThis incident has been resolved.14h 54mResolved
Feb 16, 2026⚠️ Partial Service Degradation – Cloudflare R2This incident has been resolved.48 minResolved
Jan 22, 2026Incident Update – Pencil Queue ClusterThis incident has been resolved.44 minResolved
Dec 5, 2025Cloudflare Incident — Possible Impact to R2 OperationsThis incident has been resolved.4h 24mResolved
Nov 18, 2025Degraded Performance / Partial OutageThis incident has been resolved.16h 53mResolved
Nov 14, 2025Scheduled maintenanceThe scheduled maintenance has been completed.30 minScheduled
Nov 13, 2025Scheduled maintenance windowsThe scheduled maintenance has been completed.30 minScheduled
Nov 7, 2025Degraded PerformanceOur systems experienced degraded performance when the Redis instance reached its memory limit, which caused temporary issues with user login. The issue has since been resolved, and Redis memory limits have been adjusted…-107 minResolved

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 Pencil 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 Pencil 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 Pencil 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 Pencil outage in this window ran 41d 20h, against a mean recovery of 2d 19h. If you depend on Pencil 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.