# Understanding the Deflection report

> Knowledge base deflection lets users self-serve common inquiries allowing customers to find a quick solution to their questions without speaking to an agent.

Source: https://help.kustomer.com/en_us/deflection-report-rkH6qvjwU

Last updated: 2026-05-21T22:34:50.877Z

Knowledge base deflection helps customers self-serve common questions by directing them to relevant help content or AI-generated answers before they need to speak with a support agent. This can reduce incoming conversation volume, help customers get answers faster, and let your team focus on requests that need human attention.

The **Deflection report** helps you understand how well your deflection efforts are performing and where you can improve your knowledge base or AI response coverage.

**Who can access this feature?**

**User types**

Managers can access reports.

  

### In this article

*   [What is deflection?](#deflection)
*   [Deflection report metrics](#metrics)
*   [Deflection Success Rate chart](#success-rate)
*   [Article Performance table](#ArticlePerformance)
*   [Deflection Topic Coverage chart](#TopicCoverage)
*   [Search Queries table](#SearchQueries)

What is deflection?

In customer service, deflection means helping customers resolve their questions without needing a human agent. Deflection can happen when customers are guided to knowledge base articles or when an AI response answers their question using information from your public knowledge base.

At Kustomer, you can encourage customers to self-serve by setting up article deflection in a [conversational assistant](https://help.kustomer.com/conversational-assistant-interactions-S1_U8ggt_#ArticleDeflection), [email](https://help.kustomer.com/email-deflection-BkAddmUd8), or [form](https://help.kustomer.com/knowledge-base-deflection-in-a-form-rkCIM8h9I). Organizations with access to AI-powered responses can also use AI to respond to customer inquiries with answers generated from public knowledge base content. To learn more, see [Use AI to respond to customer inquiries](https://help.kustomer.com/use-ai-to-respond-to-customer-inquiries-rkUFDaYK2).

## Access the Deflection report

To access the Deflection Report, select **Reporting**, and then click **Deflection**.

If AI response reporting is enabled for your organization, the report includes two tabs: **Article deflection** and **AI response**. The **AI response** tab is only available when the required AI response reporting settings are enabled.   
  

### Deflection report metrics

The report shows 4 metrics that let you see how successful your deflection efforts have been.

![](https://cdn.kustomerhostedcontent.com/media/570fad9d9001bc1000163b28/401a0453f8db5280f041c57f2774df97.png)

The following metrics are shown:

*   **Count of Deflections**
    *   **The Article deflection tab** is the total count of conversations that were deflected within the selected date range and did not require resolution by an agent.
        
    *   **The AI response tab** is the total count of conversations that were deflected and did not require resolution by an agent. 
        
*   **Customer Hours Saved** is the total amount of time your customers saved awaiting a resolution within the selected date range. This value is generated by multiplying your organization's _Count of Deflections_ by your organization's _Median First Resolution_ time.
*   **Agent Hours Saved** is the total amount of time saved by your team members within the selected time range. This value is generated by multiplying your organization's _Count of Deflections_ by your organization's _Average Conversation Handle_ time.
*   **Deflection Success Rate** is the ratio of successful deflections over all conversations where deflection was attempted.

### Deflection Success Rate chart

This chart shows a comparison of the Deflection Success Rate metric versus the amount of Deflection Attempts, which is the count of unique conversations where deflection was attempted. 

![](https://cdn.kustomerhostedcontent.com/media/570fad9d9001bc1000163b28/38f2b385dd216276179905e5a05df9cf.png)

The following metrics are shown:

*   **No AI Response/Article offered** is when the inquiry topic entered by the customer did not match any knowledge base articles or an AI response could not be generated. Whenever a conversation’s Last Deflection Status is equal to no match, it will be counted in this metric.
*   **Offered** is when an article or AI response was offered in a chat, but the customer abandoned the conversation without interacting with the chatbot further; or when deflection was offered in a form. Whenever a conversation's _Last Deflection Status_ is equal to `offered`, it will be counted in this metric.
*   **Unsuccessful** is when articles, or an AI response, were offered but the conversation was still transferred to an agent. Whenever a conversation’s _Last Deflection Status_ is equal to `rejected`, it will be counted in this metric.
*   **Successful** 
    *   **Article Deflection tab** is when articles were offered and the inquiry was resolved without handoff to an agent. Whenever a conversation’s Last Deflection Status is equal to accepted, it will be counted in this metric.
    *   **AI response tab** is the total count of conversations where an AI response was given and the conversation was either marked as helpful 👍🏼 , the customer abandoned the chat or the chat was marked as ended, or the conversation was not transferred to an agent. 
*   **% Deflected** 
    *   **Article deflection tab** is the ratio of the count of conversations where articles were suggested, and the conversation was marked as resolved / the total amount of conversations where conversation.lastDeflectionAt fell under the range.
    *   **AI response tab** is the ratio of the count of conversations where an AI response was given, and the conversation was either marked as helpful 👍🏼 , the customer abandoned the chat or the chat was marked as ended, or the conversation was not transferred to an agent / the total amount of conversations where `conversation.lastDeflectionAt` fell under the range. 

### Article Performance table

This table shows a list of all of the articles that were suggested in a deflection attempt and provides data to help you understand how each article is performing.

**Note:** This table is only available when viewing the Article deflection tab.

![](https://cdn.kustomerhostedcontent.com/media/570fad9d9001bc1000163b28/d81ffbb9062fee1ce73e863ec3a79041.png)The following columns are available:

Column

Description

Article Name

The title of the knowledge base article that was suggested.

Last Updated

The last time the suggested knowledge base article was updated.

Offered Count

The count of unique conversations where the article was suggested based on the customer’s inquiry topic.

Click Count

The count of times the article was suggested and then clicked or viewed by the customer.

Resolution Rate

The count of unique conversations where the article resolved the customer’s inquiry, divided by the count of unique conversations where the article was offered.

  

### Deflection Topic Coverage chart

This chart shows the percentage of search queries that returned at least one article, or AI response, in their results.

![](https://cdn.kustomerhostedcontent.com/media/570fad9d9001bc1000163b28/a250735ed84d05fac64c0e1bb1489fcf.png)

For AI deflection, the current chart definition is the count of distinct conversations where `lastDeflection.status` is `accepted`, `rejected`, or `offered`, divided by the count of distinct conversations where `lastDeflection.status` is `accepted`, `rejected`, `offered`, or `no-match`, where `lastDeflection.deflectedAt` falls within the selected date range.

### Search Queries table

This table shows a list of the terms customers used to describe their support requests. This information can provide insight into how your customers think about your product and help you identify any gaps you may have in your current knowledge base, such as a feature that isn't documented.

![](https://cdn.kustomerhostedcontent.com/media/570fad9d9001bc1000163b28/fa10175425e70d86ea7b0765d5474e24.png)

The following columns are available:

Column

Description

Search Query

The text entered by the customer when prompted for their support topic.

Search Count

The count of unique times the exact search query was entered.

Articles Offered

The count of articles returned for the query, up to 3.

Resolution Rate

The count of unique conversations where this query resolved the customer’s inquiry, divided by the count of unique conversations where this query was entered.

  
**Note:** While not common, sensitive information can appear in the Search Queries table. To help minimize this risk, we recommend you follow [best practices](https://help.kustomer.com/best-practices-conversational-assistant-B1NCgLbJq#use-cases) and prompt users for their name and email within the first couple of interactions.

### AI response tab columns

Column

Description

Search Query

The text entered by the customer when prompted for their support topic.

AI Response

The AI-generated response provided by the conversational assistant. The current UI tooltip describes this as “The response given by the AI.”

Assumed Resolution %

The count of unique conversations where an AI response was given and the customer did not mark that it resolved their inquiry or asked to speak to an agent, divided by the count of unique conversations where an AI response was given. **Flag for validation:** this current tooltip wording appears ambiguous and may need PM/Eng confirmation.

Confirmed Resolution %

The count of unique conversations where an AI response was given and the customer marked it as resolving their inquiry, divided by the count of unique conversations where an AI response was given.

Resolution %

The count of unique conversations where an AI response was given and the customer marked it as resolving their inquiry, or did not ask to speak to an agent, divided by the count of unique conversations where an AI response was given.
