Assistable Outage History

After running experiments with Enterprise Managed users and white label users (with their permission from support inquiries), we noticed that user BYOK on voice is significant increasing latency, creating scenarios of no response, and potential hallucinations. This is because user keys may not be "seasoned" or high enough tier to support high frequency of API calls (aka voice session) which could cause 429 errors and 500 errors. As a temporary solution, we are using our key as a fallback until we can engineer a tiered system for checking API keys. The idea we have engineered is to check keys for their tier / limits to give them eligibility for voice use. More to come.

We had a problem with RAG pulling into the streaming responses. We engineered, tested and pushed a solution. Assistants are automatically being updated but to skip the queue of the update, just click save changes on the assistant to patch the fix on the server side.

We are seeing 404 errors from tools derived from version 1 assistant tooling (tags, notes and tasks) - we have identified the issue and currently working on a solution.

Our dashboards are showing app too busy. We are investigating the issue.

Agencies using a WL Domain to login are experiencing login issues. Use Createassistants.com/access to login. We're investigating the WL domain wrapper.