Create AI Skills

Enhance your automations with the power of generative AI by using predefined AI Skills to accelerate creating automations and make them available for reuse to Citizen Developers, and Pro Developers across solutions.

A Pro Developer creates AI Skills so the Bot Creators can use these in their automations and save time and effort.

AI Skills are created by connecting to Model connections and fine-tuning prompts by testing them with different foundational models to find the best response that addresses the business ask. These AI Skills are made available to developers for use and reuse to help accelerate creating automations across solutions. The following models are supported:
  • Amazon Bedrock
  • Google Vertex AI
  • Azure OpenAI
  • OpenAI

This topic walks you through the steps of creating AI Skills.

Prerequisites

A Pro Developer requires these roles and permissions to create and test an AI Skill.
  • Role: AAE_Basic, Pro Developer Custom role
  • Permission: Bot Creator
  • Setting: Administration > Settings > AI Data Management > Data logging settings must be enabled. The Automation Admin can enable this setting for the Pro Developer
    Note: When you update to AI Agent Studio Automation 360 v.34 release, ensure your Automation Admin enables this setting for you to avoid getting an error message saying 'you do not have permission', when you access or execute an existing AI Skill that was created in the previous Automation 360 release.

See Roles and permissions for AI Tools

Other requirements:

Besides the roles and permissions the Pro Developer must be connected to a Bot Agent 22.60.10 and later. As part of testing the Model connection, you would have to run the bot on your desktop. Hence ensure the Bot Agent is configured to your user. If you have to switch connection to a different Control Room, see: Switch device registration between Control Room instances.

Procedure

  1. Log in to the Control Room and navigate to Automation > Create new or ‘+’ icon and choose AI Skills.
  2. Provide a name and description and click Create & edit to display a template outline. Let us create an example with the name Address Parser.
  3. In the AI Skills screen, click Choose model connection to choose from the available list of Model connections you have access to.
    These Model connections are created by the Automation Admin and assigned to your user with a custom role.
  4. After selecting a Model connection, the AI Skill is set up with the default parameter settings that is optimal for the chosen model. You can change the settings as required.
    AI Skill parameters
    The parameter values for creating a Prompt is populated based on the selected foundational model. For details of parameter settings for the supported foundational models, see Understanding parameter settings for supported foundational models.
    Note: You can set different parameter values to test and determine the values that are best suited for your use case. Changing the parameter values will influence the model response.
  5. For the Prompt you create in this AI Skills screen, you can click the Data logging switch to enable data-logging for this AI Skill.

    Enabling the switch will capture detailed logs for this AI Skill such as the prompt-text, response, and the model parameter settings that will be available for review in the AI > AI governance > AI prompt log screen.

    This feature gives the Pro Developer a granular control of the AI Skill to decide what data should be logged in AI governance. This is useful for preventing sensitive information from getting displayed in the logs. Disabling this switch from the AI Skills screen would log partial data in AI governance. Logs containing critical information of an AI Skill such as the prompt-text and the response will not get logged. This is critical for using generative AI securely, with AI governance.

  6. Now you can start creating a Prompt and add prompt inputs, as required. Let us go over an example to walk you through the steps.

Example:

The Pro Developer would create an AI Skill with the name: Address Parser that will be used to parse and extract the address from different types of documents during document processing for data extraction. This AI Skill will focus on extracting the address information from documents. The template will be made available to Citizen Developers who would reuse this as an action in their automation.

Create AI Skills

  1. You have already selected a Model connection from your available list (see step 3 above) and are now going to begin composing your Prompt.
  2. In the Prompt field enter:
    Parse the $inputAddress$ & return formatted as:
    • street: street
    • city: city
    • state: state
    • zip code: zip code
  3. Click out of the Prompt entry field.
  4. The Prompt Input section gets auto populated with placeholder prompt inputs for which you would define values. In this case, the $inputAddress$ Prompt Input field gets created by the system.
    The Prompt is meant to return a response with the street, city, state, and zip code of the address formatted in separate lines.
    Note: You can also add a Prompt Input manually by clicking Add prompt input.
  5. Next enter the following address in the Prompt Input Address field: '1502 royal oak dr, tx, 75243'.
  6. Click Get response to get a response from the model based on your Prompt.
    Note:

    Test and try different prompts and Prompt Input values to get the desired response from models and finalize on the one you are most satisfied with.

    Prompt data details could contain PHI, PII or other sensitive data you choose to enter in the Prompt. We recommend being mindful of this when testing and executing a Prompt.

  7. When you are satisfied with the response, Save the AI Skill.

Click on the ellipsis next to an AI Skill to view and access actions available to the Pro Developer.

AI Skill actions

Actions Function
Move AI Skills Click on this action to select the location where you want to move the AI Skill to, as per your folder permissions.
Check in the AI Skill Lets you check in an AI Skill to a different folder. The Status of the AI Skill updates and displays in the folder you checked in the Prompt Template. Example: if you checked in the AI Skill to the Public folder, then the Status label displays Public.
View AI Skill Opens the AI Skill displaying details.
Edit AI Skill Lets you edit the AI Skill.
Note: The Pro Developer has this permission.
Copy AI Skill Lets you copy an existing AI Skill to create a new one with the same details. You have to provide a different name though, as there cannot be duplicates of an AI Skill.
Note: The Pro Developer has this permission.
View references Lets you view references to other bots that are directly dependent on the current one where this AI Skill has been used.
Delete AI Skill Lets you delete an AI Skill.
Note: The Pro Developer has this permission.

Next steps

Your next step would be to check-in the AI Skill to make it available to Citizen Developers from the AI Skills package.

Why would you check-in an AI Skill?

After creating an AI Skill, check it into the Public folder. This will let the Pro Developer, and Citizen Developer use it from the AI Skills package in the production environment.

For reference, see:

A Task Bot, with one or multiple embedded AI Skills can be added to a larger automation that would run a complete workflow scenario.

Note: When you create or test an AI Skill in the AI Skills screen, the success or failure details along with the model responses can be viewed in Administration > Audit log and Administration > AI governance navigation. See AI governance

As the next step in your sequence of tasks, go to Use AI Skills in a Task Bot.