Conversational Insights deletes data processed through the console after the following amounts of time, depending on the data type.
Conversational Insights also uses generative AI models for some of its features, which have their own data governance policies.
Conversational Insights abides by the following logical deletion policies for each data type:
Conversations: When you delete a conversation from either the Conversation Hub or the Conversations tab in Quality AI, you also remove it from the Conversational Insights databases. Your deletion immediately removes all analysis results related to the conversation, such as highlights, sentiment, topic annotations, and Quality AI scores.
Topic models: When you create a topic model,Conversational Insights keeps the topic model until you request to delete it. Conversational Insights removes topic models and topics only when you request their deletion.
Quality AI scorecards: When you create a Quality AI scorecard, Conversational Insights keeps the scorecard until you request to delete it. Conversational Insights removes Quality AI scorecards and questions only when you request their deletion.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[],[],null,["# Data retention in Conversational Insights\n\nFor general data deletion information, see the [Google Cloud data deletion policy](/docs/security/deletion).\n\nConversational Insights deletes data processed through the [console](https://ccai.cloud.google.com/insights/projects/global/locations/global/highlights) after the following amounts of time, depending on the data type.\n\nConversational Insights also uses generative AI models for some of its features, which have their own [data governance policies](/vertex-ai/generative-ai/docs/data-governance).\n\nConversational Insights abides by the following logical deletion policies for each data type:\n\n- **Conversations** : When you delete a conversation from either the **Conversation Hub** or the **Conversations** tab in Quality AI, you also remove it from the Conversational Insights databases. Your deletion immediately removes all analysis results related to the conversation, such as highlights, sentiment, topic annotations, and Quality AI scores.\n- **Topic models**: When you create a topic model,Conversational Insights keeps the topic model until you request to delete it. Conversational Insights removes topic models and topics only when you request their deletion.\n- **Quality AI scorecards**: When you create a Quality AI scorecard, Conversational Insights keeps the scorecard until you request to delete it. Conversational Insights removes Quality AI scorecards and questions only when you request their deletion."]]
