Skip to main content
The end-of-conversation summary in Agent AI is generated using the Kore.ai XO GPT module by default. If you need a different model — for example, for language or quality reasons — you can host a model in Agent Platform or another server and provide its API endpoint. The custom summarization workflow uses the Custom Dialog Task option: when the conversation ends, Agent AI triggers the configured dialog, which fetches the conversation, generates the summary, and displays or saves it.

​
Configure Auto Summarization with Custom Dialog Tasks

  1. Set up a service node to fetch the conversation transcript using the ChatHistory API. The API response includes the conversation summary.
  2. Send the transcript to your Summarization endpoint and save the result in a context variable.
  3. Create a string-based entity node to display the summary from the context variable.
  4. Ensure the dialog is enabled for the Agent AI chat or voice channel and the app is published.
  5. Go to Agent AI > Widget Settings > Agent AI Settings > Agent AI Channel Specific Settings > Auto Summarization > Auto Summarization Model, and select a dialog task under the Custom Dialog Task option.
Dialog Task flow for Summarization: Dialog Task Flow for Summarization