AI Agent Report
Effectiveness of your AI agents.
Last updated
Was this helpful?
Effectiveness of your AI agents.
Last updated
Was this helpful?
This Analytics section presents an overview of your AI agents’ performance.
This feedback helps measure user satisfaction with the AI's responses when using AI action blocks like “Answer AI” and “AI Agent”, provided “Collect User Feedback” is enabled.
Up-votes indicate that the AI's answers are satisfactory.
Down-votes typically suggest the answers were not helpful, often due to questions falling outside the AI’s current training scope.
A high number of down-votes usually signals that the AI model may need additional training to handle those types of queries effectively.
Gives you a summary of how many AI credits are used up by your AI agents. Check how many AI credits you have by going to Settings > Billing.
Score indicating customer satisfaction among users who interacted with AI-generated answers.
This report displays the topics discussed and referenced by users during conversations. You can create new topics by assigning a title and a description to help the LLM identify and interpret them correctly.
Note: Topics counts are updated daily (NOT real-time). Any new topic or change to an existing one requires retraining all questions.
This section describes the sentiment and emotion expressed by end-users when asking questions to the AI agent. Understanding user sentiment helps identify frustration, satisfaction, or confusion during interactions. Tracking emotional tone over time can reveal trends in user experience and guide improvements to AI responses.
