Ada outage history

We are investigating elevated latency affecting the Ada dashboard in the US2 region. Customers may experience slow loading of Conversation View, conversation transcripts, conversation search, and analytics dashboards.

Query performance in US2 has returned to normal baseline levels and all affected endpoints. Conversation View, transcripts, conversation search, and analytics dashboards are responding at expected speeds.

We are currently investigating reports of delays to conversations appearing in the conversation view. Users may not see conversations appearing immediately in the conversation view at this time. An update will be provided in the next 30 min.

We have identified the cause of delayed conversations in the conversations view. The team is currently reviewing solutions, and we will be providing another update within the next 30 minutes.

A fix has been implemented and we are seeing conversations beginning to appear normally in the conversations view. Conversations may take up to 10 minutes to appear while the fix is running. We will continue to monitor the fix, and provide an update in the next 30 min.

This incident has been resolved. Timing for conversations appearing in the conversations view has returned to normal. Thank you for your patience.

We are investigating delayed delivery of AI Agent messages affecting some customers. End users may experience a long pause before receiving a reply, and in some cases may not receive a reply at all. Live agent handoffs are not affected and continue to work normally. Our engineering team is engaged and we will provide a further update within 30 minutes.

The issue has been identified and a fix is being implemented.

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 investigating reports of increased handoffs to live agents that take place during playbook execution.

The issue has been identified and a fix is being implemented.

A fix has been implemented and we are monitoring the results.

We are continuing to monitor for any further issues.

This incident has been resolved.

We are currently investigating an issue where users cannot select availability rules variables in playbook (V1 + V2)

This incident has been resolved.

We are investigating reports of clients being unable to access their ai agent dashboards.

The issue has been identified and a fix is being implemented.

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're investigating reports of admins being unable to access pages of their Ada dashboard. Admins may occasionally see a 403 error when accessing their backend dashboards.

We've identified additional impact to this incident. Some end users may experience their chat sessions failing to load.

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.

Authentication to MCP server is failing due to an outage at WorkOS. A fix for the same has been deployed and is being monitored by WorkOS. Incident page: https://status.workos.com/

WorkOS fix is now effective, and we have stopped monitoring the issue.

We are working on finding the cause of the issue.

The root cause has been identified as a security policy on our SMTP server.

A fix has been deployed, and queued Zendesk Emails are being sent out now.

We've identified an issue affecting some AI Agent conversations that use playbooks. In affected conversations, the AI Agent may transfer the conversation to a human agent before completing the playbook's steps, which can reduce automated resolution. Our engineering team has identified the cause and is working on a fix. We'll post another update within the hour, or sooner if there's news.

A fix has been implemented and we are monitoring the results.

Overall AI Agent conversation handling is at normal levels while we prepare and roll out a permanent fix for the underlying issue. Some conversations that use certain playbook configurations may still be affected until it's fully deployed, if you're seeing this, please contact support and we'll help in the meantime.

The team was able to identify the root cause and a fix is in place.

Some customers are experiencing issues with the Ada Dashboard. This is affecting Ada Dashboard users only in the form of pages being unable to load, especially the Testing and Conversation View Page.. Chatters interacting with your bot are unaffected. We’re aware of the issue and our team is actively working on getting everything back to normal. We're sorry for the inconvenience this causes. We will continue to share status updates every 30 minutes.

Our team has identified an apparent root cause (a third party vendor) and our team is currently implementing a fix for the issue with the Ada Dashboard. Thank you for your patience as we work on a resolution. Apologies for this inconvenience. We will continue to keep you up to date every 30 minutes.

We are continuing to work on a fix for this issue.

A fix has been implemented and we are monitoring the results.

We are continuing to monitor for any further issues.

This incident has been resolved.

We are currently investigating the issue.

The issue has been identified and a fix is being implemented.

A fix has been implemented and we are monitoring the results.

The incident have been resolved.

We are currently investigating this issue.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

We are currently investigating an issue affecting some of our platform's background processing. During this time, you may experience: - Delayed or missed bot replies on some conversations - Stale or delayed knowledge answers, where recently updated content may not yet be reflected - Delays in proactive messages and webhook deliveries Live chat is currently operating at or near normal levels, though some customers may notice intermittent slowness.

Identified and resolved an issue affecting some internal background data processing. Our team corrected it and confirmed all systems have returned to normal operation.

We're investigating reports of failed handoffs. A subset of users are unable to handoff. We'll provide updates to the incident every 30 minutes

We are continuing to investigate this issue

We’ve identified that the scope was much more limited, and most clients have not been affected.

A fix has been implemented and we are monitoring the results

The incident has been resolved

We are currently investigating a reported delay in the conversation view for new conversations - currently we are seeing an average delay of 5-10 minutes for new conversations entering the dashboard

The root of the issue has been identified and we are currently working to resolve the latency observed in the dashboard.

A fix has been implemented and we are monitoring the results.

This incident has been resolved.

Some customers are experiencing issues with our chat services. This is affecting all chatters interacting with Ada bots in the form of the chat widget failing to load. We’re aware of the issue and our team is actively working on getting everything back to normal. We're sorry for the inconvenience this causes. We will continue to share status updates every 30 minutes.

We have determined this outage is only affecting AI Agents on the US Cluster - US2 and other clusters are functioning normally.

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 investigating elevated error rates affecting AI Agent responses. A small subset of requests are experiencing timeouts, which may result in increased handoffs to live agents. Our team is actively investigating the root cause and will provide updates as more information becomes available.

We have identified the root cause of the elevated error rates affecting AI Agent responses. Our engineering team is actively rolling out a fix. Customer impact remains low and stable.

Our engineering team continues to roll out the fix. Error rates remain stable and we are monitoring for improvement. We will provide another update in 30 minutes.

Our engineering team continues to apply the fix across all services. Customer impact remains stable and low. The rollout is in progress and we will provide another update in 30 minutes or when the issue is resolved.

A fix has been applied and error rates have returned to normal. Emergency handoffs have dropped to zero. Our team will continue monitoring overnight to confirm full resolution. We will provide a final update once we have confirmed stability.

The certificate rotation issue has been fully resolved. Error rates have returned to normal levels and services are operating as expected. No further impact is anticipated

We are investigating reports of ai agents that are unable to respond to user messages. End user's on the web channel report the message "Failed to send message. Tap to retry."

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.

Some customers are experiencing issues with our Voice services. This is affecting some chatters interacting with Ada Voice bots in the form of references to Ada bot processes being intermittently voiced to chatters. We’re aware of the issue and our team is actively working on getting everything back to normal. We're sorry for the inconvenience this causes. We will continue to share status updates every 30 minutes.

We are continuing to investigate this issue.

Our team has identified the problem with Ada Voice and we're implementing a fix for the issue. Thank you for your patience as we work on a resolution. Apologies for this inconvenience. We will continue to keep you up to date every 30 minutes.

A fix has been implemented and we are monitoring the results.

Based on our Engineering Team's investigation, we have determined the scope of this issue is limited to a very small number of clients and affected conversations. We are continuing to work on the issue, but moving forward will be communicating on this issue on an individual basis.