Configuring the IS Process Tool

The IS Process tool triggers a process in BMC Helix Innovation Studio. The tool initiates and manages IS workflows, using a structured configuration that defines how processes run and how results are retrieved. Configuring the IS Process Tool involves specifying the process name, input parameters, and expected output variables, enabling AI agents to interact dynamically in the workflow.

An agent calls a specific IS Process tool based on the tool's description and provides input parameters based on the input parameters defined in the tool's configuration. The agent automatically maps user intent to the parameter schema defined in the tool configuration, ensuring that all required fields to generate an output are supplied in the expected structure.

If you want to specify any additional behavioral rules, such as JSON formatting requirements, default parameter values, or constraints, you must explicitly define them in the agent instructions. These instructions guide the agent in preparing and formatting the payload while still adhering to the tool’s configurations.

Click here to view the examples of instructions to be added in the Agent Instructions

Example 1: 

When a user asks "what is the weather today?", call the Weather Tool with information about the user's city and units of measurement.
Always politely ask the user about the city and units if they didn't provide this information in the same query.

Example 2:

When a user asks details about the product, call the Product Tool using RFC‑compliant JSON:
{{
  "query": "<query phrase including version>",
  "limit": 10,
  "product": "<expanded product name or empty string>"
}}

To configure the IS Process Tool

Use the following configurations when configuring the IS process tool.

1. Log in to HelixGPT Agent Studio.
2. Click Tools.
3. Click Add tool/toolkit.
   In the  Add Tool dialog box, enter the following values:

   Field name	Description
   Name	Enter the tool name.
   Type	Select the IS process tool from the drop-down list.
   Description	Enter a valid description for the tool.
   Configuration	Define the tool configuration in the JSON format. Specify the following settings Setting Description process_name The name of the IS process to be invoked. input_parameters (Optional) The input parameters required to invoke an IS process. The list can be empty if your process doesn't require any inputs. name The name of the input parameter. This must match the variable name in the process. description The description of the parameter. This helps the LLM understand how to set the input value. For example: If the parameter is Name, write the description as:  "Full name of the user.  This is a required parameter." type The string value of a Python type. This informs the LLM about the expected input format. For example: Use "int" for integers, "str" for strings optional (Optional) The boolean flag that indicates whether the parameter is optional. Default value: False output (Optional) The list of process variables that must be returned to LLM as a process result. If the output value is empty, all the process variables are presented as output. request_overlay_group (Optional) Request-Overlay-Group header. It's recommended not to set this value if it is not required in the IS process. Default value: 1 (custom mode). Use 0 for Base mode. For more information about the customization layers, see Customization layer . Sample configuration: Click to view the sample configuration ​{   "process_name":"com.example:GetWeatherForecast",   "input_parameters":[       {         "name":"city",         "description":"The city for which to get the weather forecast, this is a required parameter",         "type":"str"       },       {         "name":"units",         "description":"Unit of measurement for the forecast, valid values are `metric` or `imperial`, this is an optional parameter that the user can specify, you should default to 'metric'",         "type":"str",         "optional": true       }    ],   "output":["result"],   "request_overlay_group": 1 }​

   Providing a reference link to the user

   The IS process tool can optionally provide a reference link to the user for the data it returns. This reference link serves as a source for the returned data, enabling end users to verify the information, explore further details, and take follow-up actions based on the information.
   
   To provide the reference links to the user, specify the following output variables in the Configuration field of the IS process tool.

   Output variables	Description
   web_url	The URL of the page that references the data
   title	The title of the page that references the data

   Supported Process Variables

   The following table lists the supported variables for input and output parameters to be mentioned in the IS process tool configurations.

   Variable type	Supported	Python type	Accepteble values / notes
   Attachment	❌ No
   Boolean	✅ Yes	bool str int float	(case insensitive) true false "true" "false" 1 0 1.0 0.0
   Date	✅ Yes	str int	String format must match the platform definition
   Date/Time	✅ Yes	str int	String format must match the platform definition
   Decimal	✅ Yes	str int float
   Floating	✅ Yes	str int float
   Integer	✅ Yes	str int
   Object	✅ Yes		Any value
   Record	✅ Yes	dict	Example:
   Selection	✅ Partial	str int	Support only for the selection integer value, not the selection option name
   Text	✅ Yes	str	Any value will be converted to a string by IS
   Time	✅ Yes	str int	String format must match the platform definition
   List	✅ Yes	list	The list of values and the value characteristics depend on the value type (see above)

Related topic

Invoking an AI agent from the process