Architecting Real-Time Speech Analytics Alerts for Supervisors

Hello. I am at a small company and we are trying to set up real-time speech analytics for our supervisors. We want to trigger a notification to the supervisor when a call starts going poorly. I see that Genesys Cloud has ‘Sentiment Analysis’, but I am not sure how to get the alert out of the system and into a dashboard or a chat message. Does anyone have a simple way to do this without having to hire a developer?

Hey Fat59. I handle the network for our remote agents and I can tell you that the ‘Real-Time’ part of speech analytics is the hardest part. You cannot just check a box in the UI to send a Slack message. You have to use the Notification API to subscribe to the conversation topics. If you do not have a developer, you might be out of luck, because you need something to listen to those messages and then trigger your alert.

I am an AWS architect and I have built this using a serverless approach. You can point the Genesys Cloud EventBridge integration at an AWS Lambda function. The event contains the sentiment score updates as the call is happening. The Lambda can then use the Slack API to post a message to your supervisor channel. It is a very clean way to do it and it is very cheap to run. You just need someone who knows a little bit of Python.

Kaz33 is correct. As a dev building a custom desktop, I use these sentiment events to change the color of the agent’s screen to red if the sentiment drops too low. It is a great way to give the supervisor a visual cue without them having to read a chat message. Fat59, if you are a one-man shop, you might want to look at some of the AppFoundry partners who have pre-built dashboards for this. It might be easier than building it yourself.