# Analyze KB Article Generation Results

There are two ways to generate Knowledge Base articles from information in the Data Source that's connected to your application/bot.&#x20;

1. Navigate to **Content Generation > Knowledge Generation Clustered Tickets**, choose **Job Configuration** from the **Settings** pull-down menu and then click the **Generate Knowledge** button.\
   \
   The results for this option are returned on the [**Knowledge Generation Clustered Tickets**](https://docs.aisera.com/aisera-platform/content-generation/analyze-kb-article-generation-results#knowledge-generation-clustered-tickets-window) window.<br>
2. Start from the **Agent Assist** application/bot and click the **Generate Knowledge from Individual Ticket** button.\
   \
   The results for this option are returned on the [**Knowledge Generation Individual Ticket**](https://docs.aisera.com/aisera-platform/content-generation/analyze-kb-article-generation-results#knowledge-generation-individual-ticket-window) window.

<figure><img src="https://3281977978-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvBFXjH9S1CAy9f5hzg5Q%2Fuploads%2FNr6jEfnR6fhOSXAobxnP%2Fknow_gen_both.png?alt=media&#x26;token=e71d4a49-672c-4d9b-ab48-d3cb23cfae02" alt=""><figcaption></figcaption></figure>

### Knowledge Generation Clustered Tickets Window

Once the Job has run successfully, you can view the clusters in the **Knowledge Generation Clustered Tickets** window. All the Representatives of the  documents across all clusters will be displayed in descending order based on the Tickets count.&#x20;

And the corresponding **Similar Documents** will be displayed for each representative if found as shown below.

<figure><img src="https://lh7-us.googleusercontent.com/docsz/AD_4nXedh4vr4UyozJA8jUwkPPg7a_lLRuYvy3P3KaizoFrbxoeGwTDwsdPUpzyM1cs2Mlp7BKxpRDTuX-mlbBwvm78EiKrcmfLVlIrhqezW0BXrfZO7JObDkivnM5sc90eciDFSIN-4SRJD1DB7gWBGQiYqLdxOF6vHBcEdX_xfZTSw-CmZnhRbNlc?key=MGYyqw-PPxQdRaE6NPnphw" alt=""><figcaption><p>Knowledge Generation Window</p></figcaption></figure>

Click on one of the **Knowledge Clusters** to open the **Knowledge Details** page. You can view the tickets that were used to generate a Knowledge Base Article (KBA), in the right pane of the **Document Details** page.

<figure><img src="https://aisera.gitbook.io/~gitbook/image?url=https%3A%2F%2F2983236984-files.gitbook.io%2F%7E%2Ffiles%2Fv0%2Fb%2Fgitbook-x-prod.appspot.com%2Fo%2Fspaces%252FiZkLJr3EjXkd2tHYiQJP%252Fuploads%252FFW7ffhQ6UGiwOC0mPO8D%252Fkb_origin_tickets.png%3Falt%3Dmedia%26token%3D874d6754-5d75-4400-b469-a29820161a4b&#x26;width=768&#x26;dpr=4&#x26;quality=100&#x26;sign=f8b8209c&#x26;sv=1" alt=""><figcaption><p>Knowledge Document Details Window</p></figcaption></figure>

To see the ticket(s) that contributed to a Knowledge Base Article:

1. Select **Content Generations > Knowledge Generation** in the Aisera Administration Application (Admin UI).
2. Open a generated document from the knowledge generation list table.
3. The representative ticket from which the KB is generated is displayed in the right pane in the **Knowledge Document Details** page.

### Editable Document Titles <a href="#h_01jtpfj2ntjhybve0vajbvaha8" id="h_01jtpfj2ntjhybve0vajbvaha8"></a>

You can edit the title of a document directly within the Aisera Admin UI.

**To Edit a Document Title:**

1. Navigate to **Content Generation → Knowledge Generation** in the Aisera Admin UI.
2. Click on any document.
3. An **Edit (pencil)** icon will appear next to the document Title.
4. Click the pencil icon to open a window where the **Title** field is editable.
5. Update the Title and click **OK**.

<figure><img src="https://support.aisera.com/hc/article_attachments/36439201405581" alt=""><figcaption><p>Edit a Document Title</p></figcaption></figure>

The updated Title is saved and reflected immediately in the document list.

### Bot User Feedback Ratings

Your bot users can provide feedback for documents that you generate using the Aisera Gen AI platform.

<div align="left"><figure><img src="https://3281977978-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvBFXjH9S1CAy9f5hzg5Q%2Fuploads%2F1zXoxg6NyymG1i85N28b%2Faccuracy_a.png?alt=media&#x26;token=a5430a3b-1f26-42b9-9b51-aff809299ae4" alt="" width="375"><figcaption><p>Feedback Acccuracy Options</p></figcaption></figure></div>

Your bot users have the option to provide feedback with the following choices:

* **Highly Accurate:** This option indicates complete satisfaction with the generated answer.Comment
* **Moderately Accurate:** This option should be selected when the generated document is mostly correct, but has some issues. Sub-options are available to provide more specific details about the issue.
* **Inaccurate:** This option is for when the generated document is incorrect. There are also sub-options available to specify what went wrong.

The sub-options that are available to the users change based on the radio buttons that the users choose.

<figure><img src="https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FiZkLJr3EjXkd2tHYiQJP%2Fuploads%2FUqLl6FigeBvFmUmGashd%2F4.png?alt=media" alt=""><figcaption><p>Options and Sub-Options</p></figcaption></figure>

Your bot users have the option to edit and resubmit their feedback. They can also delete the feedback, which will reset the section, making it appear fresh with all radio options unselected. The user can then choose to add new feedback or ignore it.

### **Accuracy Feedback Search Filters**

There is a **Search** filter for **KB Article Feedback** called **KB Accuracy Feedback**. This allows you to filter and view generated documents based on the feedback your bot users have provided.CommentThe **KB Accuracy Feedback** field has also been added to the tabular section of the **Knowledge Generation** page, so you can see the corresponding feedback for each document.

<figure><img src="https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FiZkLJr3EjXkd2tHYiQJP%2Fuploads%2FfFVnX1ugJkH3vEUBvtrE%2F5.png?alt=media" alt=""><figcaption><p>Accuracy Feedback</p></figcaption></figure>

To view these feedback fields in the list view on the **Knowledge Generation** page, navigate to **Add/Remove Columns** (represented by **three dots**) and add the field.

<div align="left"><figure><img src="https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FiZkLJr3EjXkd2tHYiQJP%2Fuploads%2F6Dgf7tgapkGzkIu6TCrf%2F6.png?alt=media" alt="" width="563"><figcaption><p>Add Feedback Columns</p></figcaption></figure></div>

#### Additional Comment Fields for Generated Knowledge

The feedback mechanism for generated knowledge includes an ‘Additional Comment’ text field. \
This allows you to provide more context or specific input about the quality or content of the generated document.

**To write to Additional Comments fields:**

1. Navigate to **Content Generation → Knowledge Generation**, and click on any of the generated knowledge items.
2. In the side panel of the knowledge details page, you will see the available feedback options.
3. Select a feedback option and, if needed, add further details using the ‘Additional Comment’ field to share input on document quality or other concerns.
4. Click the Submit button to save your feedback.

You also have the ability to:

* Edit their submitted comments using the Edit button.
* Delete existing feedback and provide a new comment, if needed.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXfy7QzhkLpK54qAJ9T4oBGJAQdlthQ9wr17x9VpRY6Vbba2bxzQR6P11URDImEW_moLrf3Y5sDF9QtynxS6ah1s39sghiTCMDOUT0T5XVmuWPqSEY_JyqPRruJEkUt516X2SNMxWMcS0wcx_exeJv8?key=qlcwZD7a9HlKKbOKhWT_lQ" alt=""><figcaption></figcaption></figure>

### Knowledge Generation Individual Ticket Window

The **Knowledge Generation for Individual Ticket** window contains many of the same features as the **Knowledge Generation Clustered Tickets** Window.&#x20;

Use the filters to customize the results list.

<div align="left"><figure><img src="https://3281977978-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvBFXjH9S1CAy9f5hzg5Q%2Fuploads%2FiO8RJp2Ad7bm0sEfJj7t%2Find_filter.png?alt=media&#x26;token=5191d0b8-fdcf-4710-9c99-1d74515bebf4" alt="" width="375"><figcaption></figcaption></figure></div>

Search for Knowledge by description or key words. You can also click on a document in the list to open the document or edit the document title, as described above.
