KB Article Generation from Ticket Comments

To ensure a complete and robust knowledge repository, the Aisera Gen AI platform allows you to extract key insights from Ticket Comments, often overlooked by agents.

Why Extract Solutions from Ticket Comments?

Agents often overlook the inclusion of Resolution Notes for closed tickets.

Consequently, you may want to review the comments to extract solutions and generate knowledge articles that can be added into your knowledge base. Using this feature can improve your knowledge coverage, simplify your job, and enhance the bot user's experience.

The primary objective in using Ticket comments is to enhance overall knowledge coverage.

By granting customers easy access to a wide range of solutions and information, you simplify the process of creating a knowledge base from scratch. This, in turn, improves the customer experience.

The valuable information extracted from comments offers a holistic view of the Ticket Resolution process.

Knowledge Generation Options:

1. You can automatically upload generated documents to Aisera (Knowledge Module) during job runs for immediate RAG consumption.

2. You have an option called Manual to simply generate the document and allow the user to manually publish to the Aisera platform or SOR.

3. Regardless of the automatic upload option, you still have the capability to manually publish unpublished documents to Aisera or a configured source system.

4. You can map given fields and corresponding values while uploading the document to the source system.

For example, if there is a field called Assignee and the customer wishes to attach the Knowledge Management group value to the Assignee field, the Aisera Gen AI Platform allows you to accommodate this request using a Workflow. Accordingly, based on the customer's needs, you can map the fields and values during the document upload process.

Prerequisites

1. You have set up a Data Source Tenant Integration, an application Data Source, and an Aisera application or bot.

2. All field mappings are set up properly in the Data Source

3. You need a minimum of 30K tickets to form a homogeneous cluster.

4. Review the tickets for completeness, consistency, and accuracy before ingesting them is an essential step. The quality of the Knowledge Document results will be determined by the Ticket quality you provide.

   a. Choose the correct Data Source for ticket consideration for knowledge article generation. It is mandatory to choose the Data Source under Condition before running the Generation job.

   b. Choose the right Type of tickets - Incidents or Service Requests

   c. Select only tickets that have good-quality Comments and are in sync with the Description and Title of the ticket. Tickets with titles, descriptions, and comments that are not related will generate a low-quality knowledge article.

   d. Choose tickets with a status of Closed or Resolved in the Conditions window. This recommendation is based on the assumption that closed and resolved tickets tend to have valuable comments that provide meaningful resolutions. However, it's important to note that the Aisera system has the capability to scan and extract meaningful resolution notes from all tickets, not just limited to tickets in the Closed or Resolved statuses.

5. Ensure that you have ingested all relevant comment fields from the Data Source system that you have chosen for your Aisera application. Knowledge article generation considers comments to be of utmost importance, so it's crucial to include all types of comments present in the source system. If you're working with more than one Data Source, check for the Comments field in each source, because each source may use a different field to store their comments, so it's essential to understand these fields and ingest them accordingly

6. To enable generated document uploads to a source system, it is important to create an Upstream Data Source.

7. Select the Data Source Type as either Downstream or Upstream.

   1. Choose Downstream if the purpose is to ingest data from external sources.

   2. Choose Upstream if the goal is to upload the generated documents to the source system.

When you choose Downstream Data Source, you don't have to enter additional parameters; the Aisera Gen AI Platform uses the Data Source that is associated with your application or bot for the ingestion.

However, when you choose Upstream Data Source you need to add specific values (as shown in the following table) because you don't want to write the generated knowledge articles back to your Ticket repository. Use the steps in the following table to add your Upstream information.

Set the Data Source Mapping (Title and URL are mandatory, so the Knowledge Article can be uploaded).

Running the Knowledge Generation Job

The Knowledge Generation job can be found on the AI Learning -> Knowledge Generation tab.

Before running the Knowledge Generation process, follow the configuration steps mentioned below.

Step 1 - Set the Condition Parameters

1. Go to Actions → Configuration

2. Use the Knowledge Ingestion Configuration window to filter the Tickets by Data Source, Status, and Ticket Type.

Multiple selections for a single field will be treated as options (using the OR operator) while multiple field name conditions will be treated as multiple parameters (using the AND operator) where you can have multiple conditions for a field. For example, In the Conditions window, you can choose both Data Source and Ticket Type (AND operator) while for the Ticket Type option, you can only choose betwwne Incident, and Change Request, you can't choose both (OR operator).

1. The Data Source selection is mandatory. You have to choose one Downstream Data Source as the data source that contains the Tickets that you want to gather the comments from. The rest of the parameters are optional. IMPORTANT NOTE: There is currently a 40K ticket count limit on the Max Tickets Count field to prevent performance issues.

Step 2 - Configure the Post Generation Option

1. Select the Post Generation configuration option

2. By default, Auto Publish to Data Source will be set to Yes

Auto Publish - Yes: This feature gives you the option to automate the entire process of Knowledge Article generation and publishing. When you use this option, you can see the generated Knowledge Article in the draft state of your source system so you can make any necessary modifications. Once published, you can use it with your Aisera application because it has been added to your data source.

When you use Auto Publish, you must specify the Upstream Data source as the destination where the document will be automatically published. Additionally, the you can also specify a Template that you want to use when publishing the document.

Template (Optional): Select a template for publishing the generated document, from the Aisera Generated Knowledge Template drop-down menu. The template options include KCS and Default.

When you're done setting the configurations, click OK.

NOTE: It is mandatory to map the fields to which the different document sections will be loaded in the source system. Some customers may store the document details under specific fields; hence, it is important to configure the field mapping before we publish. All the details are documented under the configuration section.

Step 3 - Start a Knowledge Generation Job

After the configurations are set, click on the Generate Knowledge button (next to the Action button). You will get an acknowledgement saying the job has triggered and is in progress. You can monitor the status by clicking on View Job in the acknowledgement message or by navigating to Settings-> System jobs -> Generic jobs -> Search for KB Generation.

Knowledge Generation Logic

Before you proceed with the analysis of the Generated knowledge, take a moment to familiarize yourself with the knowledge generation logic in order to establish a correlation with its functionality.

Ability to View Knowledge Base Article Generation Processing Steps

The Knowledge Generation window includes a Data Processing Funnel that allows you to visualize the data processing for content generation by presenting each stage as part of a processing funnel.

After you have integrated a Data Source with your Aisera tenant instance, associated a Data Source with your bot, and the KBA Generation job is complete, you can review a detailed breakdown of the processed data:

Steps to Access:

1. Navigate to Content Generation > Knowledge Generation and select your required configuration.

2. Click the Generate Knowledge button.

3. Once the job completes successfully, you will see the knowledge clusters.

4. Choose the Data Processing Funnel button to expand the funnel and view the details, as illustrated in the following screenshot.

Breakdown of Data Processing Stages:

• Total Tickets:

  • Represents the total number of tickets in the selected ticket data source/s on the day of execution.

  • You can click on Total Tickets to navigate to SOR -> Tickets, where they can see the list of tickets.

• Filtered & Processed Ticket Set: This stage displays the list of tickets that remain after applying filters in Action → Configuration and removing those that do not meet preprocessing criteria. Preprocessing Criteria:

  • The ticket title and at least one of the following fields—comments or resolution notes—must not be empty.

  • Comments must have a timestamp.

  • Very Good and Good quality tickets that were already part of previous clusters will not be reconsidered.

You can click on Filtered & Processed Ticket Set to navigate to SOR → Tickets, where you can view the processed tickets. The grey box beside this stage represents tickets that do not meet the filtering criteria. This section is non-clickable.

• Tickets with Resolution:

  • Represents the subset of filtered tickets that contain a solution.

  • The grey box beside this stage represents filtered tickets that do not have a solution.

  • You can click on Tickets with Resolution to navigate to the Ticket Details Page, as shown in the screenshot.

• Total Clusters:

  • Displays the number of ticket clusters formed, which are visible on the Knowledge Generation page.

  • After clicking on this box, the you can see the total clusters formed in the Knowledge Generation page.

Limitations:

• The Data Processing Funnel is not available for past jobs (jobs that have already been executed).

• The funnel is not available when the job filter is set to ALL.

Visibility Into Ticket Quality

Recognizing that knowledge quality is directly proportional to ticket quality, the classification feature puts tickets into three categories: Very Good, Good, and Poor.

This classification allows you to evaluate the ticket quality and, consequently, the resulting Knowledge Base Article quality.

• Very Good – A ticket that has a resolution and also has acknowledgment from the end user.

• Good – A ticket that has a resolution but no acknowledgment from the end user.

• Poor – A ticket that has no resolution.

During KBA Generation, only tickets that are rated as Very Good and Good are considered, while Poor quality tickets are excluded.

Steps to Access Ticket Quality Details:

1. Navigate to Content Generation > Knowledge Generation and select your desired configuration.

2. Click the Generate Knowledge button.

3. Once the job completes successfully, you will see the knowledge clusters.

4. Choose the Tickets with Resolution(Purple Box)/ Without Resolution (grey box) in the data processing funnel or click on the ticket count at each cluster level, to access the Ticket Details Page, that provides comprehensive information about each ticket.

Ticket Details Page Overview:

• ID: Shows the unique identifier of the ticket.

• Title: Presents the ticket's title.

• Ticket Type: Indicates the type of ticket (such as, incident, problem, request, or alert).

• Priority: Reflects the priority level assigned to the ticket from customers' Ticket Management System.

• Quality: Specifies the quality classification of the ticket as determined by the KBA Generation job, based on the presence of a resolution.

• Resolution Category: Identifies the category under which the ticket's resolution falls.

The Fixed categories include:

• Cannot Be Self-Resolved – Internal Fix Needed: Issues arising from internal company systems that require specific personnel intervention like Developer.

• Agent Support Required for Resolution: Issues that the user can partially resolve but necessitate assistance from an agent for certain steps, such as granting permissions.

• Absence of Information: Cases where no resolution exists, which falls under Poor category.

• Resolution Without Feedback: Situations where a solution is provided, but the end user has not confirmed that the issue is resolved.

• Resolution with Feedback: A situation where a solution is provided, and the end user has confirmed that the issue is resolved.

• Quality Classification Reason: Provides the rationale for assigning a particular quality category to the ticket. example say for 'Resolution with Feedback" - The agent provided a resolution action which the user followed and confirmed that it resolved the issue.

• Created Date: Indicates when the ticket was created.

Additional Features:

• Filtering: You can filter tickets based on any of the columns mentioned above to streamline their review process.

• Exporting: There is an option to download the ticket information, allowing you to share details with the IT agents for further action, such as adding resolutions to tickets that don’t have a resolution.

This feature empowers you to monitor and improve the quality of your tickets, leading to more accurate and valuable knowledge base article generation.

Download Tickets from Total Tickets Data Point in Data Processing Funnel

You can now download a CSV file containing ticket details directly from the 'Total Tickets' step in the data processing funnel.

To Download a CSV file with Ticket Details:

1. Go to Content Generation > Knowledge Generation

2. Select a job run executed after April 23, 2025 (when funnel feature was added).

3. Click on ‘Data Processing Funnel’

4. In the funnel, select the first step: Total Tickets

5. A CSV file will automatically load, listing all ticket details available in the configured data sources at the time of execution.

   

View/Analyze Knowledge Generation output

After the Job has finished running successfully, you can view the clusters in the Knowledge Generation tab. All the recommended documents across all clusters will be displayed in descending order based on the Tickets.

Functional Details in Knowledge Cluster Page

Search:

The system will allow users to search for 'Knowledge Clusters' or 'Knowledge Documents' (both have the similar names). You can input the desired knowledge cluster or document name to retrieve relevant results. If no search result found, the application displays the message, No results found under the Knowledge Document section.

Filter options: Users can click on the "+" icon and add the following fields.

Job Run on: This shows the list applications associated with completed job runs.

Similar Documents: This is a drop-down menu displaying options for Yes and No:

Yes filters the documents in the return list by similarity.

No filters the documents in the return by dissimilarity.

Published: This will display the list within the external source knowledge repository (Upstream data source) where you uploaded the documents via a job run example, such as ‘ServiceNow’ or ‘Salesforce’, along with the ‘Aisera’ datastore option.

Users: This will display the list of users who triggered the Knowledge Generation job for that application.

Template: This is a drop down menu that includes the Default and KCS options.

Default: If you don't choose a template, the knowledge article format will default to this template. The default document format that is generated by the Aisera platform looks like the example below.

KCS: KCS is the standard template. Refer to the link for KCS Template: https://library.serviceinnovation.org/KCS/KCS_v6/KCS_v6_Practices_Guide/030/030/020/010

Knowledge Clusters: The bar graph will display the clusters in descending order. Each cluster represents a distinct set of similar Ticket pools.

When you click on a cluster, the Recommended Knowledge Document associated with that cluster is filtered in the table column, to keep it consistent with other pages. Users will have an option to choose from the various data visualization options as shown below. There is also a download option.

• Knowledge Document cluster records

  The table column displays the following fields:

  • Knowledge Cluster : Which holds the knowledge cluster name

  • Knowledge Document: This column holds the recommended knowledge document that is generated for the specific cluster.

  You can click on the Knowledge Document, which will route you to the corresponding Knowledge Document Details page, where you can view the generated document.

  • Tickets: It will display the Tickets count that are related and used to form a cluster.

  • Template: It will display the Template of the document.

  • Date: It holds the Date & Time of the cluster when it has been extracted.

  When the configuration is set to AutoPublish, the documents are generated and saved to the data source that you have designated as the Upstream source.

Troubleshooting a 0 Cluster scenario

There is a possibility that there will not be any similar tickets found resulting in zero clusters. This situation is more likely to occur when a very small number of tickets are inserted as input, where no clusters can be formed. In such cases, even if auto-publish is enabled, no Knowledge Base articles will be automatically published. This is because the absence of clusters indicates a lack of similar tickets, making the generated documents less valuable for the customer, due to the infrequency of the tickets.

Additionally, consider a scenario where 1000 tickets are present, but no clusters are found; if auto-publish is enabled, we would end up publishing 1000 documents to the source system, leading to an influx of unwanted documents for the customers, causing concerns.

To address this issue, we have implemented the following solution:

• Generate a cluster for each ticket, assuming that if no cluster is formed, each ticket is considered different. This allows us to create multiple clusters, displaying ticket-specific documents under the 'Recommended Knowledge Document' section.

• Keep 'Auto Publish' turned OFF, which means that even if the configuration states 'YES,' the document will not be automatically published to the source system."

• For now, if you need the document to be published, please contact our Customer Success Team. We will help you publish the requested document.

Knowledge Document Details side panel

Navigate to ‘knowledge cluster page’ -> click on any of the cluster -> And click on the recommended document -> System will take user to specific ‘Knowledge Details page’

Last updated: Specify the Date and time when the document is updated in Aisera.

Created On: Specify the Date and time when the document is generated.