Overview of AI Agent Reporting

In BoldDesk, the AI Agent Report is part of the broader analytics and automation suite that helps you monitor and optimize how AI agents are performing across customer interactions. The main purpose of this report is to provide insights into how BoldDesk’s AI Agent is handling customer queries, automating tasks, and contributing to overall support efficiency. This article thoroughly explores the different metrics featured in the AI Agent Report.

How to Access the AI Agent Report

1. Log in to your BoldDesk portal.
2. Navigate to Artificial Intelligence Module > Performance > AI Agent Report.

Overview Statistics Metrics

The overview statistics widget provides the following metrics:

Filtering Options

You can use filter options and save views to customize how you analyze AI Agent performance across your support operations over a preferred time period. Common filter criteria include:

• Date Range Filter
• AI Agent Name
• Resolution Category
• Resolution Type

Date Range Filter in AI Agent Reports

Selecting a time period allows you to filter and analyze AI Agent performance metrics over a specific duration. This helps you track trends, compare performance, and make data-driven decisions.

AI Agent

The AI Agent filter allows you to narrow down report data based on specific AI agents configured in your system. This helps you analyze performance metrics for individual AI agents—especially useful when multiple bots are deployed across different departments or channels. By selecting a specific AI agent, you can gain targeted insights into its effectiveness, usage patterns, and contribution to support operations.

Resolution Category

The Resolution Category refers to the classification of each customer interaction managed by the AI Agent, determined by the outcome of the engagement.

1. Resolved

The AI Agent successfully handled the entire query without human intervention. The resolution type is categorized, namely:

• Confirmed Resolution - This is the resolution where a customer affirms that their issue has been resolved by the AI Agent, leading to the conclusion of the conversation following their confirmation.

2. Escalated

This displays the conversations where the AI Agent identified that the query was too complex, sensitive, or beyond its scope, and therefore transferred the conversation to a human agent without resolving the issue. This resolution type includes:

Transferred to Agent: The customer actively requests human assistance by clicking “Talk to Person,” prompting the AI Agent to hand over the conversation based on the configured workflow.
Agent Takeover: A human agent manually takes over the conversation by assigning it to themselves, typically when they observe the need for intervention.

3. Abandoned

Represents conversations where the AI Agent began handling a customer query, but the customer disengaged before a resolution was reached. This typically occurs when the AI requests additional input or clarification, but the customer fails to respond. In such cases, the conversation remains unresolved and is categorized under the “Left Before Answer” resolution type. This metric helps identify drop-offs in engagement and areas where the AI experience may need improvement.

Resolution Type

These resolution types categorize how the AI agent handles and closes conversations, offering valuable insights into support efficiency, automation effectiveness, and the level of agent involvement.

1. Confirmed Resolution

The issue was resolved and explicitly confirmed by the customer. This indicates successful communication and customer satisfaction.

2. Transferred to Agent

The ticket was initially handled by AI or automation but then escalated to a human agent. Shows the limits of automation and when human intervention is needed.

3. Agent Takeover

An agent manually took over the ticket from the AI or another agent. Indicates proactive support or escalation due to complexity.

4. Left Before Answer

The customer abandoned the conversation before receiving a response. Could indicate dissatisfaction, impatience, or poor timing.

Conversations Widget

This widget provides a detailed overview of all conversations handled by the AI Agent. It offers insights into how each conversation was managed, including resolution types, customer engagement, and whether the issue was resolved, escalated, or abandoned. This helps support teams monitor AI performance, identify trends, and make data-driven improvements to the customer experience.

By selecting ‘View Details’ in the Conversations Widget, you can access a complete breakdown of the conversation flow, including customer interactions and AI responses.

Saving View

Once you’ve applied filters in the AI Agent Report dashboard, you can save the configuration as a custom view for future access.

1. Navigate to the AI Agent Report dashboard.
2. Apply your desired filters.
3. Click Save to open the “Save View” dialog.
4. Enter a name for your view and choose an access scope:
   • Private – Only visible to you.
   • Any Agent – Visible to all agents.
   • Group – Visible to selected groups.
5. Click Save to finalize.

Your saved view will appear in the Views panel on the left side of the dashboard.

Additionally, you can;

• Set as Favorite – Pin frequently used views to the top for quick access.
• Set as Default – Automatically load a specific view when opening the dashboard.
• Edit or Delete Views – Modify filters or remove views that are no longer needed.