Microsoft Copilot Studio – Analyze user sentiment from agent conversations
We are announcing the ability to analyze user sentiment from agent conversations in Microsoft Copilot Studio. This feature will reach general availability on March 31, 2026. How does this affect me? Copilot Studio uses AI models to analyze the tone, language, and user interactions throughout the conversation to calculate an overall sentiment score. The new sentiment analysis is an additional metric to understand customer satisfaction. Sentiment analysis works alongside existing CSAT scores and will help you quickly identify sessions with negative sentiment, enabling you to investigate issues and continuously improve your agent’s performance with the following features: Analyze a sample of all sessions. Automatic availability for customers with at least 10 sessions with questions that have triggered generative answers in the past 7 days. Sentiment is calculated for each user message in the sampled sessions and then all messages are aggregated for a single sentiment score for the session. Each session is classified as positive, negative, or neutral, based on all user messages within that session. The sentiment score is calculated and refreshed once a day. What action do I need to take? This message is for awareness, and no action is required. Message ID: MC1262498
The post Microsoft Copilot Studio – Analyze user sentiment from agent conversations appeared first on M365 Admin.
Published on:
Learn moreWe can help you with Microsoft Copilot Studio – Analyze user sentiment from agent conversations
If you want help implementing, troubleshooting, or improving this product, contact us and we’ll point you in the right direction.
Related posts
Microsoft Copilot (Microsoft 365): Local inferencing
Local inferencing expands Microsoft Copilot’s sovereign controls by enabling AI inferencing for supported Copilot interactions to occur within...
Dynamics 365 Customer Service: Quality evaluation supports knowledge source in criteria
Criteria questions can now use knowledge sources to help evaluate customer interactions. This allows organizations to ground evaluation criter...
Microsoft Viva: Ability for leaders to publish Power BI reports
Microsoft Viva Insights is extending its report publishing capabilities from analysts to leader personas such as Chief Officers, Managers and ...
Dynamics 365 Customer Service: Detailed quality evaluation score breakdown
Evaluation details now include a scoring breakdown at the overall, section, and question level. Users can see how the final evaluation score w...
Dynamics 365 Customer Service: Support Not Applicable answer option for quality evaluation criteria
Criteria questions now support a Not Applicable answer option. When a question is marked as not applicable, it is excluded from scoring instea...
Dynamics 365 Customer Service: Inactivate quality evaluation records
Quality managers can now inactivate evaluation records that should no longer contribute to scoring or reporting. Inactive evaluations are pres...
Microsoft Teams: Granular Conditional Access for Teams meetings
Granular Conditional Access for Teams meetings gives organizations greater control over access to sensitive meetings. Administrators can apply...
Customized PowerBI reports behavior after major report updates
Microsoft Viva Insights customized Power BI reports will remain tied to their original report versions and won’t auto-update with major report...
Microsoft SharePoint: Changes to the FAQ web part authoring experience
The SharePoint FAQ web part will shift AI-assisted FAQ creation to Copilot in SharePoint, while retaining manual FAQ editing in the web part. ...
Microsoft 365 Copilot: Federated Copilot connectors support create, update, and delete actions
Microsoft 365 Copilot’s federated connectors will support create, update, and delete actions in third-party services starting October 20...