AI Skills package updates

Review the updates in released versions of the AI Skills package such as new and enhanced features as well as fixes and limitations. The page also lists the release dates of each version, and the compatible Control Room and Bot Agent versions.

Versions summary

The following table lists the versions of AI Skills package released either with an Automation 360 release or as a package-only release (in descending order of release dates). Click the version link for information about updates in that package version.

Version Release date Release type Bot Agent version Control Room build
3.0.5 15 October 2024 Package-only; post Automation 360 v.34 release 22.60.10 or later 23035 or later
3.0.3 27 September 2024 With Automation 360 v.34 (Sandbox) release 22.60.10 or later 23035 or later
2.0.6 17 June 2024 With Automation 360 v.33 (Cloud) release 22.60.10 or later 23035 or later
Note:
  • To download an individual package (updated in an Automation 360 release where you want only the package), use this URL:

    https://aai-artifacts.my.automationanywhere.digital/packages/<package-file-name>-<version.number>.jar

  • For AI package, the naming convention is: bot-command-ai-<version.number>.jar

    For example, bot-command-ai-1.0.2.jar

For detailed steps on downloading a package and manually adding it to the Control Room, see Add packages to the Control Room.

3.0.5

  • Compatible Bot Agent: 21.60.10 or later
  • Compatible Control Room: 23035 or later
What's changed

When creating a Model connection, even if there is a mismatch with the model name in the Azure OpenAI console and the model name configured in AI Agent Studio, you can continue creating the Model connection as long as the Deployment ID is common

When creating a Model connection using the Azure OpenAI models, while setting up authentication parameters in the Test connection phase, ensure you enter the exact Deployment ID as it appears in the Azure OpenAI console. The model used in Azure deployment must correspond to the model you select from the Choose a model drop-down list in the Connection settings phase.

For example: If the you choose GPT-4 from the Choose a model drop-down list, and the mapped name for the GPT-4 model in the Azure OpenAI console is deploy-gpt-4, then you would have to enter that exact name in the Deployment ID field for the validation to be successful.

In Automation 360 v.33 release, because of the discrepancy, you would not be able to proceed any further and would be blocked from creating the Model connection. We have modified this behavior for the AI Skills package version 3.0.5, to let you continue creating the Model connection in spite of the discrepancy. You would see the warning message in the back-end stating the discrepancy, which could result in the model response metrics to vary.

For example: If you choose GPT-4 from the Choose a model drop-down list, and use the Deployment ID name for GPT-3.5 from the Azure OpenAI console, the model call in the back-end would call the GPT-3.5 model instead of GPT-4, which could result in differences in model-response.
Fix

When you are testing a Model connection or AI Skill on your machine, but are connected to a remote device for running the Bot Agent, clicking on the Get response button in the AI Skills screen twice was displaying an error message and would not allow you to complete the task. This issue is now resolved using the latest version of the Recorder package v.3.3.1 for running the desktop operation. This was a limitation in Automation 360 v.33 release.

3.0.3

  • Compatible Bot Agent: 21.60.10 or later
  • Compatible Control Room: 23035 or later
What's changed

AI Skills package

The Generative AI Prompt Template package has been renamed to AI Skills package in Automation 360 v.34 release.

Additionally, when using the AI Skills package > Execute action in a Task Bot, with Grounded Model connections displays fields with the returned citations in a table format. The response goes to a $SampleString$ variable and a table variable gets automatically selected to display the citations. The table displays two keys within each citation. One is the content segment displaying the information chunk and the other is the URI, which is a URL to the chunk of information in the knowledge base or data store the model call is referencing.

2.0.6

  • Compatible Bot Agent: 21.60.10 or later
  • Compatible Control Room: 23035 or later
What's new

Generative AI Prompt Template package

AI Agent StudioThis is a new package for Automation 360 v.33 (Cloud) release as part of the AI Agent Studio offering.

This package executes predefined Prompt Templates in the automations that run in the Bot editor supported by connections to foundational models such as Amazon Bedrock, Google Vertex AI, Azure OpenAI, OpenAI and others.