AI Analytics - Unthread

Introduction

Navigate to Analytics > AI to view AI performance metrics and understand how your AI assistant is handling customer inquiries. This view breaks tickets down by whether agent interaction was needed. For tickets that were deflected, you’ll see a more in-depth grouping.

Deflection Categories

We’ll highlight the deflection categories below:

• Closed by Internal User - The ticket was closed manually by an agent
• Closed by Submitter - The customer closed the ticket themselves after receiving an AI response
• Stale Intake - The user was served a reply by the bot and never replied. This can mean the answer was correct, but without user confirmation, we don’t count it as a bot deflection

AI Performance Metrics

Deflection Rate

Track how often your AI successfully handles inquiries without human intervention. A higher deflection rate means your AI is effectively resolving customer issues independently.

Response Quality

Monitor the quality of AI-generated responses through customer feedback and satisfaction scores.

Conversation Flow

Analyze how customers interact with your AI assistant and identify opportunities for improvement.

AI Generated Response History

Here you’ll find a list of all tickets within a time period (default is 30 days) along with the AI response and any user feedback provided. We intend this list to guide you as an admin to understand where your documentation sources could use some additional context or documents.

Using the Response History

• Review AI Responses - See exactly what your AI assistant is saying to customers
• Analyze User Feedback - Understand which responses received positive or negative feedback
• Identify Knowledge Gaps - Spot areas where your documentation needs improvement
• Track Performance Trends - Monitor how AI effectiveness changes over time