Skip to contentSkip to navigationSkip to topbar
Page toolsOn this page
Looking for more inspiration?Visit the

Real-time Conversation Intelligence


Conversation Intelligence helps you analyze and collect useful data insights from customer conversations in real time using AI. It provides proactive experiences like live agent assist or automated actions based on streaming conversation content.


How real-time intelligence works

how-real-time-intelligence-works page anchor

The following diagram shows the end-to-end flow from a live conversation event to language operator results delivered to your application:


Language operators in real-time

language-operators-in-real-time page anchor

Language operators use GenAI and machine learning technologies to provide additional real-time analysis and insights to your conversations. They provide instant feedback to human agents or downstream applications.

Rules in an intelligence configuration orchestrate when and how language operators run throughout the conversation lifecycle. A rule has the following components:

ComponentWhat it definesExamples
Language operatorsWhat meaning to extract from the conversation textSentiment, intent, topic detection
TriggersWhen the language operators should runOn communication (with an option for every N communications), On conversation inactive, On conversation end
ActionsWhat to do with language operator resultsSend a webhook
ContextWhat additional data to provide to language operators to improve resultsCustomer Memory, Enterprise Knowledge

With these components, you can design your intelligence configuration to react quickly to what's being said during the conversation.


Support for post-conversation analysis

support-for-post-conversation-analysis page anchor

You can use the conversation_end trigger for post-conversation analysis. This means that you can blend real-time and post-conversation intelligence applications within a single intelligence configuration to address your unique business needs.