Assembled had 47 outages in the last 2 years totaling 246h 29m of downtime — averaging 1.9 incidents per month.
There were 47 Assembled outages since March 3, 2025 totaling 246h 29m of downtime. Each is summarised below — incident details, duration, and resolution information.
We saw intermittent errors from an upstream provider and proactively forwarded all calls from our Voice AI to a live agent. Outage times: 9:27 AM to 9:46 AM Pacific
We saw intermittent errors from an upstream provider and proactively forwarded all calls from our Voice AI to a live agent.
Issue preventing interactions with the chat widget.
The issue has been identified and a fix is being implemented.
The issue has been resolved, and we are accepting calls again.
Voice calls that used our ElevenLabs model failed due to ElevenLabs Failure
Voice calls that used our ElevenLabs model failed because ElevenLab issue
We've identified an issue that is causing the draft replies and compose from notes to not work correctly.
From 6:24pm PT to 6:41pm PT, draft replies and compose from notes on the Assist product were unable to retrieve documents, which caused both operations to fail. The team has identified the underlying root cause and rolled back to a correct state and will be performing a full postmortem.
We are currently investigating an issue with some Assist Voice calls dropping.
We've identified the issue and are implementing a fix.
We've implemented a fix and Assist Voice call traffic is now restored for all customers.
We identified the root cause as service limits with a downstream service provider. We've fully resolved the issue and voice call performance has been restored. For calls that were routed to us during the period of degraded performance, any errors were successfully routed to the fallback destination in each customer's IVR.
We are currently investigating an issue with data on our Realtime Overview page failing to load.
We're continuing to actively investigate an issue with data on our Realtime Overview page. We appreciate your patience!
We've identified the issue and have started to restore data on the Realtime Overview page. We're continuing to confirm the root cause of this issue and monitor for reocurrences.
We've resolved this issue and confirmed that functionality has been restored. We identified the root cause as a recent code change with unintended impacts to our Realtime Overview page.
We are investigating an issue where certain queues are not visible on the realtime overview page for some customers.
We believe we've found the cause of missing realtime overview data, and we're implementing mitigation strategies. Missing queues are gradually re-appearing as the problem resolves.
The issue has been identified and a fix is being implemented.
For most customers who are experiencing missing certain queues from the realtime overview, the queues have now re-appeared.
A fix has been implemented, and we're monitoring the results.
The incident has been resolved. The team will continuing to monitor the implemented fix over the next two days to ensure stability.
Some Assist activities are currently inaccessible for some users. We are currently investigating this issue. There is no detected impact to Assist automations.
The issue has been identified and a fix is being implemented.
We've implemented a fix and all Assist activities are now accessible. We are continuing to monitor and investigate root cause.
We've confirmed that Assist is fully operational. We identified the root cause as a recent code change that unintentionally affected draft reply and dashboard access in specific cases. We've identified and fixed the issue to restore full functionality.
Assembled is experiencing an issue with delayed Salesforce agent state syncs for some customers. We have identified a cause and are implementing a fix.
We have pushed a fix and agent state syncs have recovered for the affected accounts.
Some metrics including adherence metrics are currently incorrect or missing for customers after April 1st at 7:00AM ET. We are currently investigating this issue and working on a fix.
We are continuing to investigate this issue.
We are continuing to investigate this issue.
We've identified the issue in our metric computation job and have released a fix. Metrics will be restored over the next few hours. We will continue to provide updates as metrics are restored.
All affected metrics have been restored and are now up-to-date. We will continue to monitor.
This incident has been resolved.
There is some staleness in agent and ticket-based metrics after March 29 1:00am UTC as they are being recomputed using data from the upgraded database. We have verified that the metric computation jobs are running, and will continue to monitor them as they make progress.
Agent and ticket-based metrics have been refreshed as of March 30th 3:50 PM UTC. We will continue to monitor the stability and performance of our systems.
We're currently investigating an issue where Assist related requests are failing or taking a long time to load.
All users have been switched onto a fallback model provider which should resolve all requests. Our engineering team is looking into longer term remediations for automatic fallbacks.
We're seeing elevated error rates on Assist related products. We've identified the root cause and are mitigating the issue.
Most features should be working again as of 11:18am PT including Draft Reply, Compose from Notes, and other copilot features after we changed model providers. We're still updating our models for some workflows and Assist for Chat features.
The issue affecting Assist-related products has now been completely resolved. Following our model provider change, we've successfully restored functionality across all impacted services. Our engineering team is looking into longer term solutions that will allow us to change model provides more quickly and seamlessly in the future.
Assembled is investigating failures to retrieve agent state data via our API beginning yesterday around 1:00 AM UTC.
Agent state data is now syncing as expected via our API and no agent state data was lost as a result of this issue. We are continuing to monitor and confirming root cause.
This is now resolved The following functionality has now been restored: viewing the Realtime Analysis page, seeing agent states from the Assembled API, and adding an ID for people via the API. We can confirm that no agent state data has been lost. From 0111 UTC to 1402 UTC, the aforementioned functionality was not available.
Between 4:27pm ET and 4:32pm ET, an infrastructural issue with one of our database nodes resulted some requests to the database failing altogether. Agent states exclusions were applied from 4:28 PM ET to 4:31 PM ET.
We're currently investigating issues with Zendesk Chat agent states not syncing into Assembled beginning around 3/19 3:45am EST. As of 12:30pm EST, Zendesk Chat agent states are now appearing correctly in Assembled. Our team is continuing to investigate the root cause and is monitoring for recurrences.
Assembled experienced a delay when syncing Zendesk agent states due to a temporary issue with Zendesk's API. The issue has now been resolved.
We are currently investigating an issue where the Assist dashboard is not accessible on reload. From 11:23 AM Pacific Time, users were experiencing failures to load Assist after loading the application for the first time. We have found a fix and are working to deploy.
From 11:23 AM Pacific time to 12:29 PM Pacific time, users were experiencing failures to load Assist. We've resolved the issue and apologize for the inconvenience.
Our email sending system is experiencing slower than normal delivery times. Our team is working to return to full email delivery over the next 24-48 hours. What to expect during this time: - Emails may take longer to reach recipients - No emails will be lost during this period - All messages will be delivered, just with some delay
After closely monitoring our email system for the past 24 hours, we're able to confirm it's now been functioning normally for the past few hours. All messages are being delivered at standard speeds, and no emails were lost during the recent slowdown. Our engineering team will continue to keep a close eye on the system to ensure everything runs smoothly going forward.
Assembled is experiencing degraded performance, which may cause slow load times.
Assembled load times are now back to normal. We appreciate your patience here. We experienced slow loading times from 12:44 PM Eastern to 12:54 PM Eastern.
Some users may still experience slow load times. We are continuing to investigate and resolve the issue.
Some users may still be experiencing slow load times. We are continuing to investigate and resolve the issue.
Some users may still be experiencing slow load times. We are continuing to investigate and resolve the issue. We appreciate your patience.
Some users may still be experiencing slow load times. We are continuing to investigate and resolve the issue. We appreciate your patience.
We’re pleased to inform you that the recent performance degradations have been resolved. We continue to actively monitor system performance to ensure stability. The performance degradations occurred from 12:44pm - 13:27pm Eastern Standard Time. If you experience any further issues, please contact our support team at [email protected].
We’ve fully resolved this issue and observed no issues with the platform’s performance during the monitoring period. We are finalizing our analysis of the root cause and are committed to ensuring our platform’s pages and reports respond swiftly.