Skip to Content
This documentation supports the 26.1 version of BMC Helix Digital Workplace Basic and BMC Helix Digital Workplace Advanced. Icons distinguish capabilities available only for the Advanced and External license levels. For more information, see the License types and features topic. To view an earlier version, select the version from the Product version menu.

 

Using BMC HelixGPT to make services requestable via chat

As a catalog administrator, you can make services requestable through chat in Employee Navigator. Chat-enabled services are supported in Digital Workplace (DWP), Microsoft Teams, and Helix Virtual Agent (HVA). Agentic catalog submission (using the Catalog Request Agent) is supported in Employee Navigator and also via the Microsoft Teams interface. You can use one of the following methods to make services available via chat: 

Using BMC HelixGPT to make services requestable via chat provides the following benefits to the catalog administrators: 

  • Save manual efforts required for using the Publish chat-enabled service wizard.
  • Avoid human errors when using disambiguation, providing variations in service descriptions, service clarification phrases, and natural language variations of the questions.
  • Achieve faster scalability by making several services requestable in a short period of time. 
  • Improve discoverability of services that help users identify the appropriate service for their queries. 
Information

Important

The following types of services are not supported via chat:

  1. Services that include a questionnaire with the following types of questions:
    • Table (multi-select)
    • Table (single-select) 
    • Repeatable group of questions
  2. Catalog Services from BMC Service Request Management
  3. Services that have a minimum quantity set to more than 1
  4. On-behalf-of (OBO) services

As an administrator, you can configure the Employee Navigator Supervisor agent, facilitating a more contextual and conversational request submission experience for users within the chat.  For more information, see Configuring the Employee Navigator Supervisor agent. 

Catalog Request Agent

The Catalog Request Agent, configured in HelixGPT Agent Studio, includes the prompts to make services requestable. It identifies and suggests the services relevant to the user's queries. After the end user approves, the agent submits the service request on behalf of the user. To learn how to edit an agent, see Managing AI agents.

The Catalog Request Agent is provided out-of-the-box with BMC HelixGPT, as shown in the following image:

Catalog Request Agent

Information
Important

The Catalog Request Agent is set up as a sub-agent within the Employee Navigator Supervisor agent configuration.

The Catalog Request Agent can temporarily shift to any of the Employee Navigator tools to respond to user queries that go beyond catalog request submission. This digression allows the agent to maintain a smooth conversational experience while addressing other questions. The Employee Navigator Supervisor agent switches the flow back to the Catalog Request agent when the user asks to return to the request submission.

For more information, see Configuring Employee Navigator Supervisor agent.

Creating a copy of the Catalog Request Agent and modifying the prompts

If you want to modify the Catalog Request Agent setting, make sure you create a copy of the agent. For more information, see Managing AI agents.

Information
Important

To make sure that the services are suggested, after creating the agent, make sure that the prompt has the following structure. All prompt sections must be present and the individual prompts cannot be blank.

Prompt structure

   

    ## Search Service

    <Prompt for creating a query to search the services based on user's query>

    ## Best Service

    <Prompt for selecting the most relevant service from the list of services>

    ## Autofill by Context

    <Prompt for predicting answers to the questionnaire based on user's query>

    ## Question

    <Prompt for selecting question to ask>

    ## Failed Question

    <Prompt for asking the question again after the user failed to answer it>

    ## Format Answer

    <Prompt for formatting the user's answer (like splitting to multiple answers or skipping the question completely)>

    ## Answers Confirmation

    <Prompt for analyzing if the user wants to submit request or change any answer>

    ## Digression

    <Prompt for analyzing intent of the query to check if we need to continue with the current flow or digress to other things like knowledge search>

    ## Services

    <Prompt for displaying services to select in markdown format, for example, like markdown table>

    ## Create Request Or Clarify
    <Prompt for checking if user agrees to create request for selected service or need something else>

 

(Optional) To configure Catalog Request Agent

As an administrator, you can modify the number of services, questions, and probable answers that the Catalog Request Agent provides to the end users. 

  1. Log in to BMC Helix Innovation Studio.
  2. From the Workspace tab, select HelixGPT Agent Studio.
  3. Click Visit deployed application to open the console.
  4. From the Application list, select BMC Helix Digital Workplace.
  5. From the Agents tab, select the copy of Catalog Request Agent that you have created and click Edit. For more information, see To clone an agent.
    In the General Configuration field, specify the following parameters:
    ParameterDescription
    services_limit

    Controls the maximum number of services that the system searches in the catalog. Among the searched services, the most relevant services that match their query is displayed to the end users.

    Default value: 10

    questions_limit

    Controls the maximum number of questions that a service can have. If a service has more questions than the number specified in this parameter, then the user is prompted to use the service request submission UI. 

    Default value: 20

    autofill_by_context

    Determines whether initial user input queries are used to auto-populate the answers to the questions.
    For example, if a user types I need to request guest parking from Monday to Wednesday next week", the system auto-populates the start and end dates for the parking request. 

    Default value - true

    If you do not want to auto-populate the answers, set the value to false.

    context_limitIndicates how many prior messages from the user will be considered for searching services and auto-populating answers.

    Default value - 3
    action_typeDetermines how a service link will be opened.
    format_answer_options_limit

    Controls the maximum number of options that a question can have to be considered for formatting the answer for options-based questions.

    Default value - 2000

    autofill_options_limitControls the maximum number of options that a question can have to be considered for auto-populating answers for options-based questions.

    Default value - 100
    question_option_limit

    Controls the maximum number of options that could be mentioned in a question text.

    Default value - 2000

    supported_servicesDefines a list of services based on the service version IDs that can be requested via chat. 
    restricted_servicesRestricts the service version IDs from being submitted via chat by the end users. 
  6. Click Save. 

Result

After the Catalog administrator has completed the configurations, the end user can submit the service requests via chat.

Employee Navigator will auto-populate the questions for which it has sufficient meaningful information from the prior conversation with the user and only ask the remaining questions in the chat. The following image shows the final service request summary that is displayed to the user to review and approve.

1768892275015-942.png

Users can modify their answers for the questions, including the auto-populated ones, before submitting the service request.

Troubleshooting

The following section describes the steps you can perform if you encounter the following issues:

Important
To perform the following steps, you must first clone the Catalog Request Agent. Always make changes to the cloned version. For more information, see To clone an agent.

Issue

Steps to perform

Service creation fails, and Employee Navigator responds with the following error message:

The questionnaire is too complex for <service name>.

Configure the Catalog Request Agent and increase the value for the questions_limit parameter.
 

Service creation fails, and Employee Navigator responds with the following error message:

I cannot find any information. Please refine your request.

Configure the Catalog Request Agent and modify the values for question_option_limit, autofill_options_limit, and format_answer_options_limit parameters, based on your requirements.

Important: This issue can occur for several reasons. If it is caused by the size of the questionnaire, adjusting the values for the parameters mentioned above should resolve it.

 

Tip: For faster searching, add an asterisk to the end of your partial query. Example: cert*

BMC Helix Digital Workplace 26.1