Bi-Weekly Product Release Notes - May 21, 2025

Features

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

Ontology

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

Ontology Generation from KB Articles

You can now generate Ontologies from the Knowledge Base Articles that you have ingested into your Aisera tenant, after adding a Data Source to your application/bot. With this release, you can generate domain-specific Ontology Entities from specific data sources (the body text of documents in private KB Articles) as well as synonymous terms for these Entities.

There are two scenarios for generating Ontologies:

1. You have created an application/bot that is not associated with the IT, CS, or HR Domains.

2. You have created an application/bot and chosen an IT, CS, or HR Domain during the creation process. In this case, your bot is using a default ontology from the specified domain.

In either use case, the process for running an Ontology Generation job is the same.

To generate an Ontology from KB Articles:

1. Navigate to the LLMs > Ontology menu item in the Aisera Admin UI.

1. Choose the + New button at the top of the window.

1. Select Ontology Generation.

1. Create a Name for your Ontology Generation Job and specify the Data Source. Enter both the Domain (if you didn’t choose one when creating your bot), and a Description of the Use Case(s) for your application/bot in the Use Cases field.

1. Click the OK button.

Now you will see a Success message that tells you the Ontology Generation Job has begun.

1. Click View Jobs within the Success message to see the job status.

2. When the job is complete, return to the LLMs > Ontology page and toggle the Review Mode switch to the ON position.

   
3. Now you can see the new Entities and their associated Synonyms at the top of the page. On each line of the results, choose the Green (left) dot to Accept the new Entity, choose the Red (right) dot to Reject the new Entity, or choose the pencil icon to Edit the new Entity.

Conversational AI 2.0

The following features have been added to Conv AI 2.0 in this release.

Try the 2.0 Workflow Search With a Test Bot

You can now ask your Aisera team to help you set up a Conversational AI 2.0 workflow at the bot level, instead of the tenant level, to test out the search and fulfillment capabilities.

If you want to try this option, ask your Aisera CSM to enable the appropriate feature flags.

Ability to Make Time-Related Requests

With this release, you can now make requests such as,

• What are the titles of the Knowledge Base Articles added in the past 40 days?

• Who won the Outstanding Team Award in the last quarter of 2025?

• How many shopping days are there until Christmas?

• Will there be any public holidays in the next 10 days?

• Do we have a long weekend at the end of the month?

If your bot is set to use Conversational AI 2.0, and the Time Detection flag is selected in the Conversational AI Policy settings for that bot.

Enhancements

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

AI Lens

The following enhancement has been added to AI Lens in this release.

Debug Workflows and Hyperflows Using AI Lens

The AI Lens feature allows you to test your bot after creation and perform some preliminary tests, if you are a customer with Administrator privileges in your Aisera Gen AI platform instance.

With this release, you can use AI Lens to see the debug information for your bot’s workflows and hyperflows while the bot is running.

To see the debug information for your bot workflow or hyperflow:

1. Choose AI Lens in your Aisera Admin UI.

2. Select your bot from the pull-down list at the top of the AI Lens window. You will see a bot interface on the AI Lens window.

3. Add a Request. (AI Lens requests will not be recorded in Aisera analytics.)

   
4. After you add a Request, you will see the bot functions on the right side of your window.

Choose the Show More link to see the flowDebugInfo and flowDebugInfo2 methods as they are running.

NOTE: You can also test Workflows and Hyperflows using the Test button on the AI Automation > AI Workflow Studio window.

Conversational AI 2.0 - Channels

The following enhancement has been added to Channels in this release.

LLM Responses in HTML if Markdown Not Supported

The Markdown text format is supported only in Webchat, Webex, and Co-Pilot; other channels treat content as HTML. Therefore, LLM responses are formatted as HTML for all channels where the Markdown format is not supported.

Aisera Gen AI Platform Upgrade

The following enhancement has been added to Aisera Gen AI Platform in this release.

Upgrade to Backend Models

As part of ongoing improvement and reliability of our platform we will be updating the large language models (LLM) used with your Aisera products. These improvements will result in increased response accuracy and reduced latency, enabling an even better experience for your users. This upgrade will not affect any existing functionality.

As part of the natural AI SaaS lifecycle, support for older models is phased out as newer, more capable models become available. Our team at Aisera has conducted extensive testing and validation to ensure a seamless and stable transition. We do not anticipate any disruption to your services.

In the unlikely event that you observe any unusual or unwanted behavior following the upgrade on 5/21, please don't hesitate to contact Aisera Support.