AI Option
The AI Option Stage is used to automatically categorize input (such as emails, forms, or user messages) into predefined options (Option-1, Option-2, etc.) based on an AI-generated response. This helps your workflow branch intelligently, reducing manual classification and improving automation.
.
AI Option
Select variable or repositories:
The dropdown displays the "Variable" value in the list.
Select variable or fields:
The dropdown displays all variable names from previous stages.
If no variables are available from previous stages, it shows 'No variables found’.
When select a variable in the first dropdown, the second dropdown dynamically displays all variables from previous stages.
Create a prompt:
“Create a prompt” field is mandatory, the validation message displays as 'Prompt is required' when the prompt field is left empty.
When you copy a variable from the dropdown, it gets inserted into the prompt in the following format:
${Variable:variableName}
After saving the form, the prompt remains exactly as entered — no formatting loss or data corruption occurs when you reopen the stage.
What is Option-1, Option-2, etc.?
In the AI Option Stage, you define multiple possible outcomes (called options) that the AI can classify the input into. These options represent categories or labels based on your use case.
Each Option has:
Label: A name that represents a category (like Incident, Service Request, etc.)
Mapped Output: If the AI's response matches this label, that option is selected and stored as the result.
Purpose of Options:
Options allow you to branch the workflow based on the AI's classification. For example:
Option Name
Meaning
Used When AI Classifies Input As
Option-1
Incident
An issue or fault to be resolved (e.g., system not working)
Option-2
Service Request
A request for something (e.g., access, installation, query)
Option-3
Change Request
A suggestion to modify/update something (e.g., software upgrade)
Example Prompt:
This are the input:
Title: A request for CRM installation.
Description: The user is requesting the installation of the CRM system to manage customer relationships and streamline operations.
Classify the above title and description into one of the following:
Option-1: Incident
Option-2: Service Request
Option-3: Change Request
Expected Behaviour:
If the AI responds with “Service Request”, the system automatically selects and stores Option-2 as the result and routes the workflow accordingly.
AI Option Under For Each Stage
Select variable or repositories:
The dropdown list displays the Variable and Repository names selected in the 'For Each' stage
Select variable or fields:
When a Variable is selected in the first dropdown, the second dropdown dynamically displays the list of available variables from previous stages.
When a Repository is selected in the first dropdown, the second dropdown displays all fields of the selected repository.
If no variables are available from previous stages, the second dropdown displays the message: "No variables found."
Create a prompt:
“Create a prompt” field is mandatory, the validation message displays as 'Prompt is required' when the prompt field is left empty.
When variable values are copied, the prompt inserts them in the following formats:
For Variables: Format: ${Variable:variableName} Example: ${Variable:eligibilityStatus}
For Repository Fields: Format: ${RepositoryName:FieldName} Example: ${Candidate_Details:Experience} -The system uses the internal names of the repository and the field when generating the token.
After saving the form, when the stage is reopened, the entered prompt appears exactly as saved without any formatting changes or data loss.
What is Option-1, Option-2, etc.?
In the AI Option Stage, you define multiple possible outcomes (called options) that the AI can classify the input into. These options represent categories or labels based on your use case.
Each Option has:
Label: A name that represents a category (like Incident, Service Request, etc.)
Mapped Output: If the AI's response matches this label, that option is selected and stored as the result.
Purpose of Options:
Options allow you to branch the workflow based on the AI's classification. For example:
Option Name
Meaning
Used When AI Classifies Input As
Option-1
Incident
An issue or fault to be resolved (e.g., system not working)
Option-2
Service Request
A request for something (e.g., access, installation, query)
Option-3
Change Request
A suggestion to modify/update something (e.g., software upgrade)
Expected Behaviour: AI Option Output Storage
When the AI Option stage is used inside a For Each loop, it evaluates the decision for each record in the repository.
If the AI responds with “Service Request”, the system automatically selects and stores Option-2 as the result and routes the workflow accordingly.
Example scenario:
If select For Each Repository: IT Ticket
Prompt to AI:
Message: ${repository:RequestTitle}
Analyze the above message and classify it into one of the following categories:
Option-1: Incident
Option-2: Service Request
Option-3: Change Request
Purpose:
We are looping through each ticket in the IT Ticket repository. For each item, the AI evaluates the Request Title and classifies the nature of the request into one of the predefined options.
Output Examples:
Request Title
AI Selected Option
Explanation
My system is crashing on startup.
Option-1 (Incident)
Sudden issue affecting normal operations.
Need VPN setup on my laptop.
Option-2 (Service Request)
A request for IT support service.
Requesting to upgrade the CRM dashboard view.
Option-3 (Change Request)
Request for change in existing system.
Expected Behaviour:
For each ticket, AI will analyze the request title and return the matching option (Option-1, Option-2, or Option-3).
This option will be stored in the defined output variable (e.g., RequestType), and can be used for routing or filtering in later stages like update record stage (update the priority)
AI Option Under Condition Stage
Select variable or repositories:
The dropdown shows variable values.
Select variable or fields:
It shows all variables from previous stages in the dropdown.
If no variables are available from previous stages, it displays 'No variables found’.
When a variable value selected in the first dropdown, the second dropdown dynamically shows the list of available variables from previous stages.
Create a prompt:
“Create a prompt” field is mandatory, the validation message displays as 'Prompt is required' when the prompt field is left empty.
When you copy a variable from the dropdown, it gets inserted into the prompt in the following format:
${Variable:variableName}
After saving the form, the prompt remains exactly as entered — no formatting loss or data corruption occurs when you reopen the stage.
Expected Behaviour: AI Option Output Storage
Scenario:
When the AI Option stage is used under a Condition stage, and the condition checks a specific variable value the AI will evaluate the prompt only if the condition is true.
Condition Logic: If ${Variable:Request} is equal to Option-2 (In the Option-2 store service request value)
Only when this condition is satisfied, the workflow proceeds to the next stage — AI Option.
AI Option: Prompt: Request: ${Variable:Request}
Based on the above content, classify which application the user is requesting service for:
Option-1: CRM
Option-2: Recruitment
Option-3: Helpdesk
Output Storage Logic:
Option-1 → AI returns "CRM"
Option-2 → if AI returns "Recruitment"
Option-1 → AI returns "Helpdesk"
Example of request:
"Please add new user access in the CRM system for our sales team."
"Can you enable candidate tracking for the new recruiter in the recruitment module?"
"I am unable to assign a support agent to new tickets, please fix the helpdesk configuration."
Expected Output (from AI Option Stage)
Request title
Selected Option
"Please add new user access in the CRM system..."
Option-1: CRM
"Enable candidate tracking for the recruiter..."
Option-2: Recruitment
"Fix helpdesk ticket assignment issue..."
Option-3: Helpdesk
Last updated