Create and manage AI エージェント

This topic describes how to create and manage an AI エージェント in the Control Room. You can perform various actions such as running, moving, checking in, viewing, editing, copying, and deleting AI エージェント, with certain permissions required for editing and deletion.

To create an AI エージェント in the Control Room:

Procedure

  1. Log in to the Control Room and navigate to Automation > Create new or ‘+’ icon and choose AI Agent.
  2. Provide a name and description and click Create & edit to display a template outline. Let us create an example -- Claim Details AI Agent.
  3. Define the agent's prompt: You will notice Generate prompt for your Agent (cloud-only feature) screen appears and ask you to input the prompt.

    The first step in creating an AI エージェント is to give it a mission. You will do this by providing a clear and detailed initial screen prompt that describes the agent's purpose in natural language. This prompt is the foundation upon which the entire agent's logic is built.

    For example, to create the Claim Details agent shown in the example, a user might have started with a concise but informative message like this:

    Your job is to retrieve claim details:
*  Retrieve policy and police report details.
*  If any information is missing, ask a human for assistance.

    This initial input provides the core requirements, which the AI エージェント Studio can then use to generate a more detailed, structured prompt. The AI エージェント Studio is designed to be flexible; you do not need to provide every single detail upfront. However, the more context you provide, the better the AI エージェント Studio can generate a starting template for you to refine.

    The system will then expand on this initial input to create a comprehensive prompt (example shown below).

    Note: The generated role/goal/action plan text varies slightly depending on the model being used. Your example cannot match this word for word, but the structure and intent will be similar.

    Example output:

    Role: You are an insurance claims processor specializing in stolen property claims, with expertise in retrieving and verifying claim, policy, and police report details using automated tools and human assistance when necessary.

    Goal:Your goal is to retrieve and verify all required details for a stolen property claim using the provided claim ID, ensuring no output value is null, and consulting a human if necessary to complete the task.

    AI エージェント- Claim Details
  4. Choose a Model Connection:Navigate to Model tab and click Choose to choose from the available list of モデル接続 you have access to. For more information on Model Connection, see モデル接続
    These モデル接続 are created by the Automation Admin and assigned to your user with a custom role. Only モデル接続 created from Automation Anywhere provided models or from bring-your-own-licenses (BYOL) are allowed. Custom model definitions are not currently supported with AI エージェント.
    Note:
    AI Agents supports:
    • OpenAI and Azure OpenAI model connections that use GPT-4o and GPT-4.1 (Standard type) models.
    • Automation Anywhere model connections that use GPT-4o.

    When choosing a model, ensure you select the most recent available version (for example, GPT-4o November 2024 or later) to take advantage of the latest stability and performance improvements.

  5. Define agent variables: Navigate to Input & Output tab. Here, you need to tell the agent what information to look for as input variables and what to provide as output variables. These variables will be used by the LLM to understand the context and communicate with the tools. The key is providing rich and descriptive language. The more detailed your descriptions, the better the LLM will be at understanding its purpose and fulfilling its goal.

    • Input variable:

      • Name: claim_id

      • Description: The claim ID for which to retrieve details

    • Output variable:

      • Name: claim_details

      • Description: Final details of the claim, including policy and police report information.

  6. Define the End-user Display: This step allows you to configure how the AI エージェント execution is presented to the user. The goal is to provide a clear and meaningful title for the task that the user sees in the Co-pilot interface. Navigate to the End-user display tab. In the Agent request title, provide a title for the task. This title is a mandatory field and is displayed when the AI エージェント runs in the Co-pilot. For example, for the Claim Details agent, the title could be Claim Details Request. This helps the user understand what the agent is doing at a glance.
  7. Add and configure tools:

    Under Tools tab, add the required automations for your agent to perform its task. In this example, you will be adding the Claim Lookup, Police Report, Data Tracker, and Policy Process automations as tools.

    Tool Name Purpose Input Variables Output Variables
    claim lookup Provides the claim details. INPUT_id: claim id claim_id: the claim id, policy_id: the policy id, stolen_property_item: the item that was stolen, claimed_replacement_cost: the replacement cost for the claim items, location_of_incident: location of the incident, police_report_id: the police report id, date_of_incident: the date of the incident, claim_status: the status of the claim, claimant_name: the claimant name, receipt: the receipt for the property in the claim
    police report Gets the police report details. INPUT_id: police report id police_report_id: the police report id, report_date: Date of report, officer_name: name of officer, officer_badge_number: badge number, incident_type: type of incident, description: description of input, incident_location: incident location, suspect_name: suspect name, arrest_made: Was an arrest made, reporting_station: reporting station
    data tracker Always calls this tool to track data you have or have not received so far data_received_or_missing_so_far: The details on the data you have received or are missing (or have null values) formatted in json data_received_or_missing_so_far_response: The data you have received or are missing so far in JSON format
    policy process This gets the details of a policy INPUT_id: The policy id policy_id: the policy id, policy_number: the policy number, policy_type: the policy type, issue_date: The date the policy was issued, expiration_date: the expiration date, status: status of the policy, premium_amount: the premium amount, payment_frequency: the frequency of payments, insured_name: the name of the insured, insured_address: the address of the insured, insured_phone: the phone number of the insured, insured_email: the email of the insured, coverage_type: the coverage type, policyholder_id: The policy holder id, coverage_amount: the coverage amount, agent_id: the id of the insurance agent, deductible_amount: the deductible amount, was_successful: True if the lookup found any data, False otherwise.

    For more information on configuring tools, see AI エージェントのツールでの設定.

  8. Define the Action Plan: The Action Plan section, is generated by the system based on your prompt and the tools you have added. It outlines the logical flow:
    • Retrieve claim details: Call the Claim Lookup tool using the claim_id.
    • Retrieve police report: Call the Police Report tool.
    • Track the data: call the Data Tracker tool.
    • Get policy details: call the Policy Process.
    • If claim details are incomplete, use the Human in the Loop to ask for assistance.
  9. Test and refine: Once you have configured everything, click Run to test your agent to ensure it behaves as expected. You can simulate a conversation with the agent, providing a claim ID and seeing if it correctly retrieves the claim details, police report, and policy information. Refine the variable descriptions and tool prompts as needed to improve the agent's performance and accuracy.
    Note:

    Note: Testing and running AI エージェント in your private workspace does not consume Automation AI Credits. For more information on credit consumption when moving to production, see AI エージェント のライセンスモデル.

    .

Next steps

Once you have created and configured your AI エージェント, embed it into your business processes and bring intelligence into end-to-end automation. For more information on adding an AI エージェント to a process, see プロセス オートメーションに AI エージェント を追加する. The following diagram illustrates the typical workflow, from agent creation to execution in a public environment.

AI エージェント Work flow

The process of moving an AI エージェント from a development environment to a public-facing one involves several key steps and user roles.

Create and test
A professional developer or automation admin creates and tests the AI エージェント.
Configure in a process
The Professional developer then configures the AI エージェント within a larger process.
Check in
The process is checked in to the repository, making it available for use.
Run in public
The process can then be run in a public workspace, allowing it to be called through the Automation Co-Pilot.
Note:

A business user with the required Automation Co-Pilot Business User license can execute the process and interact with the AI エージェント. The diagram also shows the specific permissions required for each user role to perform these tasks. For more information about the roles and permissions, refer ロールおよび権限.