Dust had 43 outages in the last 2 years totaling 31h 29m of downtime — averaging 1.8 incidents per month.
There were 43 Dust outages since December 2, 2024 totaling 31h 29m of downtime. Each is summarised below — incident details, duration, and resolution information.
The issue has been identified and a fix is being implemented.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
Google is currently experiencing degraded performance on Gemini 3 and 3.1 pro models, which is likely to impact the performance and availability of assistants using these models. You can follow the situation here: https://aistudio.google.com/status
This incident has been resolved.
Anthropic is currently experiencing degraded performance on Claude Sonnet 4.6 and Opus 4.6, which is likely to impact the performance and availability of assistants using Anthropic models. You can follow the situation here: https://status.anthropic.com/
We are continuing to work on a fix for this issue.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are currently experiencing degraded performance affecting search functionality in the EU. Users may experience slow responses or timeouts when performing searches. Our team is actively investigating and working to resolve the issue.
We are continuing to investigate this issue.
This incident has been resolved
We increased the capacity to absorb the amount of requests to agents and quickly catching up. We are investigating the root cause.
We are continuing to monitor for any further issues.
This incident has been resolved.
Between 00:00 UTC and 07:20 UTC today, EU users were unable to access Dust due to an expired TLS certificate. The Google-managed certificate for EU subdomains (eu.dust.tt, eu.connectors.dust.tt, eu.viz.dust.tt) failed to auto-renew. We identified the root cause, provisioned a new certificate, and all EU services are fully operational again. Connectors synchronization should not have been affected. Webhook-based triggers where lost during this timespan, as well as remote automation platform workflows (like n8n, make, or zapier).
We've identified the issue. We're working on a fix.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are currently experiencing intermittent issues with message processing. Some conversations may fail to send or receive responses. Our team is actively investigating.
We are continuing to investigate this issue.
The issue has been identified and we are working on a fix.
A fix has been implemented and we are monitorng the results.
We are continuing to monitor for any further issues.
We are continuing to monitor for any further issues.
We are currently investigating this issue.
We are continuing to investigate this issue.
The issue has been identified and a fix is being implemented.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are currently having latency issues on the Dust application. We are investigating actively.
We have identified the issue and are currently fixing it.
This incident has been resolved.
Agents are taking longer than normal to respond. We are actively investigating.
The latency spike have been mitigated. We are no longer receiving any reports of higher than normal agent response time
We are experiencing increased agent execution latency. We are investigating the issue and scaling agent loop processing workers to reduce latency.
Incident was resolved. We are investigating root cause to prevent reproduction.
Agents are taking longer than normal to respond. We are actively investigating.
This incident has been resolved.
We are currently having latency issues on the Dust application. We are investigating actively.
Resolved.
Anthropic is currently experiencing degraded performance on claude sonnet 4.5, which is likely to impact the performance and availability of assistants using Anthropic models. You can follow the situation here: https://status.anthropic.com/
This incident has been resolved.
We've identified an issue affecting Europe-hosted workspaces. Our team is actively working on a fix.
A fix has been implemented and we're monitoring the results.
This incident has been resolved.
We are currently impacted by an outage with our authentication provider. Login to Dust is unavailable at this time. We are closely monitoring and will provide updates as they become available.
Our provider is back online, incident resolved.
We are currently investigating an issue causing some users to experience errors when attempting to sign in. The impact appears to vary by region and network conditions. Our team is working to identify the cause and restore full functionality. More updates will follow.
We have identified a configuration issue affecting DNS resolution for some of our authentication subdomains. An updated configuration has been applied and sign-in functionality has begun to recover.
The DNS configuration issue impacting sign-in has been fully resolved. All authentication subdomains have been re-verified, and sign-in is now working normally for all users. Everything is operating as expected, and we will continue to monitor to ensure a smooth experience moving forward.
Agents using the websearch tool might fail due to an issue with our provider Firecrawl
The issue has been identified and a fix is being implemented.
The issue has been resolved, websearch is working.
We are currently experiencing an issue with our third-party login provider, resulting in an outage of authentication services. As a result, users are unable to log in to the application. This issue is impacting all users, and access to the app is currently unavailable. We are actively monitoring the situation and are in contact with the login provider to resolve the problem as quickly as possible.
The issue has been identified as originating from our authentication provider. They are actively working on a fix. Dust is still accessible through Slack.
The issue is ongoing. The problem has been identified as a major authentication outage affecting many services worldwide. We are closely monitoring and coordinating with our providers to restore access as quickly as possible. Dust remains accessible through Slack.
We are continuing to work on a fix for this issue.
The authentication outage has been fully resolved. All login services are now operational, and users can access the application normally. We continue to monitor system stability to ensure consistent performance.
Anthropic is currently experiencing degraded performance, which is likely to impact the performance and availability of agents using Anthropic models. You can follow the situation here: https://status.anthropic.com/
This incident has been resolved.
We are investing an incident where clicking to access the agent builder blocks further navigation.
The issue has been identified, a fix should be live in 10mns.
This incident has been resolved.
The Dust Slack Tools are currently encountering an authentication issue. Due to a token invalidation issue on our end, a Dust admin on your workspace will need to reconnect the slack tool via the 'Tools' subsection of the 'Spaces' tab in Dust. Performing this action will fix the issue.
We are continuing to monitor for any further issues.
This incident has been resolved.
During 29mn starting at 12:15 UTC and ending at 12:44 UTC, interactions with Dust agents in slack, as well as in any conversations containing file attachments or generated files in the Dust web app, failed by remaining stuck on "Thinking...". This was due to a missing database migration. Issue has been resolved, all attachments are now working as usual.
Due to an outage of one of our provider, some agents are currently un-responsive. Claude models are not accessible. You can follow the situation here : https://status.anthropic.com/ Some other components may be irresponsive as there's a global outage of Cloudflare services. You can track it here : https://www.cloudflarestatus.com/
This incident has been resolved.