Configuring BMC HelixGPT to offer options for unanswered questions

BMC HelixGPT enhances service efficiency by providing end users with alternative options, such as raising a service request or connecting with a live agent, when knowledge articles-related questions are not answered by BMC HelixGPT.

BMC Helix Digital Workplace Catalog administrators can configure the Fallback prompt to seamlessly route these unanswered questions into actionable requests.

Using the Fallback prompt

When BMC Helix Digital Workplace Catalog administrators use the Fallback prompt available out-of-the-box, they must specify a service that enables end users to submit a service request. By using the Publish Chat-enabled Service wizard, BMC Helix Digital Workplace Catalog administrators can either import an existing BMC Helix Digital Workplaceservice or download and import the sample service provided by BMC Software.

Click here to download the sample service.

When specifying a default service, BMC Helix Digital Workplace Catalog administrators must consider the following points:

Use a BMC Helix Digital Workplace Catalog native single-request service.
Do not localize the service or questions asked in the service.
Map only one service as a default service.
Use only the text field and text area (without RTF) type questions in the service.
Add a maximum of three questions in one service request.

To use the Fallback prompt available out-of-the-box, BMC Helix Digital Workplace Catalog administrators perform the following tasks:

Use HelixGPT Manager to copy the Fallback prompt
Use the Publish Chat-enabled Service wizard to specify the default service request
(Optional) Use HelixGPT manager to configure a live agent connect capability

Task 1: To use the fallback prompt

Step	Action	Reference in BMC HelixGPT documentation	Example
1	Log in to HelixGPT Manager and create a custom skill.	Creating skills	Click here to see the example You are an intelligent virtual assistant and you need to decide whether the input text is an information request. This is a classification task that you are being asked to predict between the classes: information or tools requests. Returned response should always be in JSON format specified below for both classes. Do not include any explanations, only provide a RFC8259 compliant JSON response following this format without deviation: {{ "classificationType": "information service", "nextPromptType": "Knowledge", "services": [ {{ "serviceName": "Dummy", "confidenceScore": "1.0", "nextPromptType": "Knowledge" }} ], "userInputText": "...." }} Ensure these guidelines are met. 0. If there are multiple possible matches for a user request, please ask the user to disambiguate and clarify which match is preferred. 1. If user input text is a question that contains phrases such as "How" or "Why", "How to", "How do" etc. then classify the input text as 'information request' in the classification field of the result JSON. The JSON format should be: {{ "classificationType": "information service", "nextPromptType": "Knowledge", "services": [ {{ "serviceName": "Dummy", "confidenceScore": "1.0", "nextPromptType": "Knowledge" }} ], "userInputText": "...." }} In case the classification type is "information service" then don't change the attribute value for 'nextPromptType' in the JSON. 2. The list of catalog services is shown below along with the corresponding prompts. Use only this list. List of catalog services and corresponding prompt types are: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Input Text: Sample input text1 Input Text: Sample input text2 Service Name: Sample Service, Prompt Type: Sample Prompt Type ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Input Text: General Request Input Text: Raise a service request Service Name: General Request, Prompt Name: General Request ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3. If there are multiple catalog services that match the input text, then show the catalog services and sort them by highest confidence. Set the "services" field in the result JSON. 'text' field should have the input text. Output JSON: {{ "classificationType": "catalog service", "nextPromptType": "Service", "services": [ {{ "serviceName": "service name 1", "confidenceScore": highest confidence score, "nextPromptType": "prompt type 1" }}, {{ "serviceName": "service name 2", "confidenceScore": second highest confidence score, "nextPromptType": "prompt type 2" }}, ], "userInputText": "...." }} 4. When your confidence on matching to a single catalog service is very high, classify the input text as 'catalog service' and show the matching service and ask the user for confirmation of the service picked. Once a single service is selected, set the "services" field in result JSON to this selected service. 'text' field should have the input text. Output JSON: {{ "classificationType": "catalog service", "nextPromptType": "Service", "services": [ {{ "serviceName": "service name", "confidenceScore": confidence score, "nextPromptType": "prompt type" }} ], "userInputText": "...." }} 5. If the user input text is a query about a. a request or a service request, b. a list of requests or a list of service requests c. an appointment or a list of appointments d. a task or a list of tasks, e. a to-do or a list of to-dos f. what is the status of request REQXXXX g. what is the details of request REQXXXX h. summarize requests i. an existing request j. contains a string like REQXXXX k. what is the status of request XXXX l. what is the details of request XXXX m. contains a string like XXXX then classify the input text as 'requests' in the classification field of the result JSON. The JSON format should be {{ "classificationType": "requests", "nextPromptType": "Request", "services": [ {{ "serviceName": "Dummy", "confidenceScore": "1.0", "nextPromptType": "Request" }} ], "userInputText": "...." }} 6. If the user input text asks for information or guidance, such as "How do I" or "Can you help," classify it as an 'information request' in the classification field of the result JSON. For example, if the user is asking for help or clarification on a process, it should be classified as an information request. 7. Based on the classification, if the request is for request, set 'classification' in JSON to 'requests'. 8. Based on the classification, if the request is for catalog services, set 'classification' in JSON to 'catalog service'. 9. If the user input text does not match with any service, you MUST set nextPromptType to Knowledge. 10. Return the response in JSON format only without any explanations. You must ensure that you return a valid JSON response. {input}
2	In the custom skill, copy the BMC Helix Digital Workplace Router prompt. This must be the starter prompt.	Copying a skill
3	To the same custom skill, copy the knowledge prompt.
4	To the same custom skill, copy the Fallback prompt available out-of-the-box.

Task 2: To specify the default service request submitted by end users

Log in to BMC Helix Innovation Studio and navigate to the Workspace tab.
Select Actions > Publish Chat-enabled Service.
The Publish Chat-enabled Service wizard is displayed.
On the Workspace tab, perform the following steps:
1. From the Provider drop-down menu, select BMC HelixGPT.
2. From the Application Name drop-down menu, select BMC Digital Workplace.
3. From the Skill drop-down menu, select the appropriate skill.
4. Click Next.
  The following screenshot shows the options on the Workspace tab:
On the Service to Chat-enable tab, select a service that you want to include.
The following screenshot shows the options on the Service to Chat-enable tab:

On the User Request tab, perform the following steps:
1. Click the Add button next to the Request Variation field.
  A blank field is displayed after the Request Variation field.
2. In the blank field, add the following text to enable raising a service request through BMC HelixGPT:
  Raise a service request
3. Click Next.
  The following screenshot shows the options on the User Request tab:
On the Questions tab, click Next.
The following screenshot shows the Questions tab:
On the Publication tab, click the Publish button.
The following screenshot shows the Publication tab:

The following confirmation message is displayed:
Click Confirm.
Click Close.

The default service is defined.

(Optional) Task 3: To configure the option to connect to a live agent

Step	Action	Reference in BMC HelixGPT documentation	Example
1	In the Fallback prompt, in the No Result Found category, add an option to connect with a live agent.	Copying a skill	Click here to see the example Fallback Options by Categories: - No Results Found: - Raise a service request: Raise a service request - Chat with a Live Agent: Chat with a Live Agent - Failed Service Request: - Raise a service request: Raise a service request - Failed Router Classification: - Raise a service request: Raise a service request - System Error: - Raise a service request: Raise a service request - Other: - Raise a service request: Raise a service request
2	Modify the Router prompt to add Live Chat classification type.	Copying a skill	Click here to see the example If the user input text is a query about connect to an agent want to talk to agent chat with live agent live agent agent then classify the input text as 'response' in the classification field of the result JSON. The JSON format should be {{ "classificationType": "response", "nextPromptType": "Response", "services": [ {{ "serviceName": "Dummy", "confidenceScore": "1.0", "nextPromptType": "Response" }} ], "userInputText": "...." }}
3	Add a new prompt of type Response.	Creating skills
4	To the new prompt of type Response, add instructions to generate cross launch link to Live Chat.		Click here to see the example {global_prompt} You are an intelligent assistant tasked with generating an HTML anchor tag based on a user query. Follow these steps: Generate an Anchor Tag: Create an HTML anchor tag (<a>) with the URL <LIVE_CHAT_URL>. Open in New Window: Ensure the anchor tag includes the attribute target="_blank" to open the URL in a new window. Anchor Text: Use text for the anchor that suggests connecting to a live agent, for example "Connect to Live Agent" or "Talk to Agent" etc. Provide Context: Include additional context in the response to inform the user that they will be transferred to a live agent for further assistance.

Result: Output after using the Fallback prompt

The following screenshot shows the option to raise a service request:

The following screenshot shows an option to connect with a live agent: