">
sevanalysis

Nomic

AI. Source: Nomic status page.

Incidents, last 90 days
4
Median to mitigation
16m
Median to resolution
21h 40m
p95 to resolution
15d 2h
Naming an upstream provider
0%
With a postmortem on the status page
0%

What failed, last 90 days

The text does not say enough to tell2
Data delayed, stale, lost or corrupted, or needing replay after recovery1
A code release introduced the failure1

Tagged by claude-haiku-5-5 from each incident's updates. See the methodology.

Incidents per month

Hatched months are before the recorded history starts.

All recorded incidents

Document processing services experiencing failures minor 2026-09-15 18:47 UTC 15d 2h

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

  1. investigating

    We've detected elevated failure rates in our document processing services. We are currently investigating the failures and underlying server health.

  2. monitoring

    Services have recovered and we are monitoring for additional failures

  3. monitoring

    All systems are again fully normal

  4. resolved

    Incident resolved.

Excerpts are shortened. Read the full incident on Nomic's status page.

Users experiencing intermittent message sending failures major 2026-09-12 21:23 UTC 15m

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

  1. identified

    Some users are seeing assistant sessions fail to send messages. Root cause is identified and a fix is underway.

  2. resolved

    Assistant sessions are now working correctly again in all regions.

Excerpts are shortened. Read the full incident on Nomic's status page.

Delays in indexing minor 2026-08-05 15:18 UTC 24h 31m

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. investigating

    We are investigating delays in document indexing that leave some documents stuck in a processing state. Assistant sessions with affected documents should be able to proceed without interruption.

  2. resolved

    The backlog of unprocessed indexing jobs has cleared for the two affected customers.

Excerpts are shortened. Read the full incident on Nomic's status page.

Elevated error rates in PDF processing none 2026-08-04 17:17 UTC 18h 48m

Failure mode: A code release introduced the failure. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. monitoring

    Some agent tool calls, as well as certain document operations such as viewing a PDF, were affected by a partial rollout of a service change in a recent deployment.

  2. monitoring

    A fix has been applied, and we are validating that the issue has been resolved.

  3. resolved

    The issue with PDF processing has been resolved.

Excerpts are shortened. Read the full incident on Nomic's status page.

Elevated rate of Authentication errors major 2026-07-16 17:22 UTC -436m

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

  1. identified

    We began seeing a substantial minority of all authentication requests to the Nomic Platform failing because of [an outage in our authentication provider, workOS](https://status.workos.com/incidents/b52fkqjzcl20). This caused many requests across the system to be rejected when...

  2. resolved

    Our authentication provider has fixed the problem and all authentication requests are now succeeding.

Excerpts are shortened. Read the full incident on Nomic's status page.

Backlog of agent session requests major 2026-07-15 17:52 UTC -663m

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. identified

    A backlog of long-running agent sessions on a single customer's instance occupied all dedicated workers for 46 minutes

  2. identified

    Long-running jobs begin completing and new work begins clearing.

  3. resolved

    All backlogged work was cleared

Excerpts are shortened. Read the full incident on Nomic's status page.

Indexing system outage major 2026-06-04 12:52 UTC 52m

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. investigating

    We experienced an outage that caused a number of indexing operations in Nomic Platform to fail; the affected subsystem has been restored, and we are working to clear the backlog of requested work.

  2. resolved

    The indexing subsystem experienced an outage on 06-04-2026; the system has been restored.

Excerpts are shortened. Read the full incident on Nomic's status page.