Release Date:  July 9, 2025

Table of Contents

Features 

Analytics 3

Universal Bot Analytics 3

Support for Google Analytics 4

Enhancements 

Knowledge Base Article Generation 6

Ability to Customize SOR Writing Failure Messages 6

Additional Comment Fields for Generated Knowledge 9

AI Model Selection for KB Generation Prompts 10

AI Workflow 11

Read-Only Option for User Input Node 11

 

Features

The following features  have been added to the Aisera Gen AI Platform in this release.

Analytics

The following features have been added to Analytics  in this release.

Universal Bot Analytics

If you choose Universal Bot when you create an application/bot in the Aisera Gen AI Platform, you can create sub-bots that have different domains to perform specific agentic tasks.

With this release, you can select your Universal bot from the bot list for your tenant (Settings > AiseraGPT) and then select Analytics > Pre-Built Analytics to see three consolidated views of insights for the sub-bots associated with your Universal app. 

The Pre-built Analytics window for the Universal app consolidates all the KPI data from the different apps related to your Universal bot, on the Requests, Sessions, and Users tabs.

Use the pull-down list to choose the bots that you want to include in the metrics data displayed on the Requests, Sessions, and User tabs.

Support for Google Analytics

You can now enable Google Analytics at the tenant level for use with your Webchat applications/bots.

To add Google Analytics:

1. Navigate to Settings > Configuration > Tools.

2. Choose the checkbox next to Enable Analytics.

Enhancements

The following enhancements  have been added to the Aisera Gen AI Platform in this release.

Knowledge Base Article Generation

The following features have been added to Knowledge Base Generation  in this release.

Ability to Customize SOR Writing Failure Messages

This release gives you the ability to customize the  error messages that can occur when publishing a document to your SOR (Source of Record)  system fails due to missing or incorrect configurations.

To publish a document to an external knowledge management system, you must create a Workflow with the appropriate endpoints and event triggers. When a bot user clicks the ‘Publish to SOR’ button, the Aisera Gen AI Platform checks to determine if the necessary prerequisites are in place.

There are two primary scenarios that trigger an error message:

1. You have not created any required flow/event (a prerequisite for publishing).
2. You have created the event/flow, but with incorrect or incomplete configurations.

The Aisera Gen AI Platform now displays targeted error messages for each of these scenarios, enabling you to identify and resolve configuration issues quickly.
 

Scenario 1: No Event/Flow Created

When you click the Publish to SOR button in the Knowledge Generation window without having the required workflow/event, the platform will now display acknowledgement popups with clear error messages. 

These messages will also appear in the Document Status column for visibility.

Acknowledgement Messages for ‘Publish to SOR’:

1. No Event Triggers Found (Either Not Created or Inactive):
   Use case: No events have been created, or the existing ones are inactive.
   Error message:
   No active event found. Please create and activate an event using the right template flow to publish the knowledge.
    
2. Event Triggers Exist Without a 'Template' Triggering Condition:
   Use case: An active event exists, but the required template trigger condition has not been configured.
   Error message:
   Template trigger condition is missing for the active event. Please configure it to proceed with publishing.
    
3. Multiple Event Triggers Found for the Same Template Condition (Active):
   Use case: More than one active event is configured with the same template condition (e.g., multiple workflows using the "KCS" template), which is not allowed.
   Error message:
   Multiple active events found for the same template. Please ensure only one active event exists per template to proceed with publishing.
    

These enhancements ensure you receive real-time, actionable feedback when publishing prerequisites are not met.

Scenario 2: Event Exists, but Configurations Are Incorrect

If the user has created the required event, but there are configuration issues, the system will display failure messages under the status column when the user attempts to publish:

1. Workflow Configuration Issues
   Error message:
   Workflow configuration error: Please review and update the configuration before retrying.
2. External/API Errors
   Error message:
   The system will show the specific error message received from the external API, providing visibility into the failure reason.

Additional Comment Fields for Generated Knowledge

We have enhanced the feedback mechanism for generated knowledge by introducing an ‘Additional Comment’ text field. This allows you to provide more context or specific input about the quality or content of the generated document.

Navigation Steps:

1. Go 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.

AI Model Selection for KB Generation Prompts

This release includes the ability to select from supported AI models directly within the UI for knowledge generation prompts.

Navigation:

1. Go to your Application/Bot Details  window and click on ‘View Policy’ under the Knowledge Generation Policy section.
   
   
2. A configuration window opens, displaying the prompt settings used for KB Article generation.
3. From the dropdown, users can now select the supported AI model based on their agreement during onboarding or sales discussions.

Supported Models Include:

• GPT-4o
• LLaMA 3.3
• LLaMA 3.1
   

AI Workflow

The following enhancements have been added to AI Workflow  in this release.

Read-Only Option for User Input Node

The User Input Workflow node gives you the ability to enter responses by typing or selecting responses from options provided. Without this Input, the flow will not proceed further during execution.

Now you can set the Node to Read Only if it contains pre-filled or informational data only.