Chat Completion - Initiate Subprocess (OpenAI) Control Tower

Display Name

Description:

Specifies the activity name that shows in your process.

Allowed Values:

One line of text (a string).

Accepted:

• Letters
• Numbers
• Spaces

Default Value:

None

Accepts Variables:

No

Example:

This is a common configuration field that is used in many examples. Refer to:

• Examples - Step-by-step use case examples, information about what types of examples are provided in the AgilePoint NX Product Documentation, and other resources where you can find more examples.

Description

Description:

Specifies an optional text description for your activity.

Allowed Values:

More than one line of text.

Default Value:

None

Accepts Variables:

No

OpenAI

Description:

Specifies the access token that connects to OpenAI.

Allowed Values:

A list of access tokens configured for your environment.

Default Value:

None

Create

Opens this Screen:

Access Token for OpenAI.

Function of this Screen:

Configure an access token to connect to OpenAI.

Model

Description:

Specifies the name of the model to use to generate text output.

Allowed Values:

A model name from the list.

When you select the access token from the access token field, this field shows the model names associated with the access token.

If the specified access token is configured with the model and the Use Model Configured In Access Token field is selected, this field shows the model name configured with the access token, and you can not change it.

Default Value:

None

Accepts Variables:

Yes

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Use Model Configured In Access Token

Description:

Specifies whether to use the model configured in the selected access token.

Allowed Values:

• Selected - Uses the model configured in the access token.

  When you select the access token from the access token field, this field is enabled.

• Deselected - Configures the model to use to generate text output.

Default Value:

Deselected

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Frequency Penalty

Description:

Specifies the frequency penalty for the LLM to use the same words or phrases in generated text output.

A high value means the model uses the same words or phrases less frequently.

A low value means the model uses the same words or phrases more frequently.

Allowed Values:

A decimal number.

Range:

• -2.00 - 2.00

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Presence Penalty

Description:

Specifies the presence penalty for the LLM model to use the same word frequently in generated text output.

A high value means the model uses the same word less frequently.

A low value means the model uses the same word more frequently.

Allowed Values:

A decimal number.

Range:

• -2.00 - 2.00

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Maximum Token Length

Description:

Specifies the maximum number of tokens that can be used to generate text output.

This value limits the length of the generated text output.

Allowed Values:

An integer.

Range:

• 1-10000

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Stop Sequences

Description:

Specifies one or more stop sequences to make the LLM stop creating text.

The model stops creating text when it finds the specified stop sequence.

Allowed Values:

A maximum of 4 stop sequences, separated by semicolons (;).

Stop sequences are specific words, phrases, or special characters other than semicolons (;).

Default Value:

None

Accepts Variables:

Yes

Example:

• Thank you;Best regards;I hope this helps
• For list items, if the stop sequence value is 11, the model generates stops generating list items after 10 items.
• If the stop sequence is a period (.), the model stops generating text at the end of a sentence.

Temperature

Description:

Specifies the temperature value for the model to control the randomness of text output.

Allowed Values:

A decimal number.

Range:

• 0.00 - 2.00

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Nucleus Sampling (top_p)

Description:

Specifies a top_p threshold value to control the randomness and predictability of text generation. This value limits the selection of possible tokens to the top_p percentage of cumulative probability.

Allowed Values:

A decimal number.

Range:

• 0.00 - 2.00

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

OpenAI

Description:

Specifies the access token that connects to OpenAI.

Allowed Values:

A list of access tokens configured for your environment.

Default Value:

None

Create

Opens this Screen:

Access Token for OpenAI.

Function of this Screen:

Configure an access token to connect to OpenAI.

Goals / Mission

Description:

Specifies the goals or rules for the LLM to generate text output.

To Open this Field:

1. On the System Instruction tab, click Set System Instruction.

Allowed Values:

More than one line of text.

Format:

• Rich text

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Skills

Description:

Specifies the skills or roles for the LLM used to generate text output.

To Open this Field:

1. On the System Instruction tab, click Set System Instruction.

Allowed Values:

More than one line of text.

Format:

• Rich text

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Input

Description:

Specifies the input content the LLM used to generate text output.

To Open this Field:

1. On the System Instruction tab, click Set System Instruction.

Allowed Values:

More than one line of text.

Format:

• Rich text

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Instruction

Description:

Specifies any guidance or information to refine the response of the model to generate text output.

To Open this Field:

1. On the System Instruction tab, click Set System Instruction.

Allowed Values:

More than one line of text.

Format:

• Rich text

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Quality Verification

Description:

Specifies any guidance or information to verify the accuracy of the generated text output.

To Open this Field:

1. On the System Instruction tab, click Set System Instruction.

Allowed Values:

More than one line of text.

Format:

• Rich text

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Output

Description:

Specifies the output format the LLM used to generate text output.

To Open this Field:

1. On the System Instruction tab, click Set System Instruction.

Allowed Values:

More than one line of text.

Format:

• Rich text

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Activity

Description:

Specifies an activity on which to run the LLM.

Allowed Values:

An activity from the list.

Default Value:

None

Accepts Variables:

No

Example:

Refer to:

• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

On Event

Description:

Specifies the status for an activity instance where the change occurs.

Allowed Values:

• Assign Work Item - LLM runs when the specified task is ready to be Assigned to a participant.
• Complete Work Item - LLM runs when a task is Completed.
• Cancel Work Item - LLM runs when a task is Cancelled.
• Enter Activity Instance - LLM runs when the activity instance starts.
• Leave Activity Instance - LLM runs when the activity instance ends.
• Reassign Work Item - LLM runs when a task is Reassigned.
• Work Item Assigned - LLM runs after the specified task is Assigned to a participant.
• Work Item Overdue - LLM runs when a task is Overdue.

Default Value:

None

Example:

Refer to:

• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

Set Trigger Condition

Opens this Screen:

Chat Completion - Initiate Subprocess Configuration > Triggering Event tab > Set Trigger Condition

Function of this Screen:

Configures an activity on which to run the LLM to generate text output

Rule Type

Description:

Specifies a rule to execute.

Allowed Values:

• IF - Specifies a rule to execute if a specified condition is true.
• ELSE IF - Specifies a rule to execute if the previous condition is false.

  To open this field, click Add New Rule .

• ELSE - The rule executes if the all the specified conditions are false.

Default Value:

1. IF
2. ELSE

Rule Name

Description:

Specifies a name for a rule in your condition.

Allowed Values:

One line of text (a string).

Accepted:

• Letters
• Numbers
• Spaces

Default Value:

Rule Name 1

Edit

Opens this Screen:

Chat Completion - Initiate Subprocess Configuration > Triggering Event > Condition Builder screen

Function of this Screen:

Creates or changes logical rules. You can put one statement inside another statement to create complex logical expressions.

Delete

Function:

Deletes the selected row.

Condition Name

Description:

Shows the name for your rule.

Allowed Values:

Read only.

Default Value:

Rule Name 1

Preview

Function:

Shows the preview of your rule.

Validate

Function:

Makes sure the rule is correct.

Rule Variable

Description:

Specifies the value to analyze.

Allowed Values:

One line of text (a string).

Accepted:

• Letters
• Numbers
• Spaces

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (Example) Configure a Condition Activity (Check Leave Approval Status)
• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

Operator

Description:

Lets you select the operators for a logical expression.

Allowed Values:

Data Type	Expression Operators
String	, ==, Starts with, Ends with, Contains, Does Not Contains, !=, Does Not Contain Data, Contains Data
Bool	==
Date Time	, ==, >, >= , <, <=, !=
Number	, ==, >, >=, <, <=, !=

Default Value:

None

Example:

Refer to:

• (Example) Configure a Condition Activity (Check Leave Approval Status)
• (Example) Configure a Condition Activity (Compare Leave Hours)
• (Example) Create Zoom Meeting

Rule Value

Description:

The value for the data variable.

Allowed Values:

One line of text (a string).

Accepted:

• Letters
• Numbers
• Spaces

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (Example) Configure a Condition Activity (Check Leave Approval Status)
• (Example) Create Zoom Meeting
• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

Add Row

Function:

Creates a condition row.

Select Nest Type

Function:

Specifies the use of logical AND and OR operators to nest conditions to use for predictions.

You must set the condition first, before you specify the nest type.

Allowed Values:

• And - Specifies the logical AND operator.
• Or - Specifies the logical OR operator.

Default Value:

AND

Indent Right

Function:

Creates the statement that is a condition of a parent statement.

Delete

Function:

Deletes the selected row.

Back

Function:

Saves the rule and goes back to the Create Condition screen.

Message Content / Map JSON Request To App Schema

Description:

Specifies how to connect the request data from the LLM to the AgilePoint process schema.

Allowed Values:

• Message Content – Specifies a text prompt that defines the content for the message.

  The LLM reads the text in this field to generate text output.

• Map JSON Request To App Schema - Specifies a payload to use to connect to the AgilePoint process schema.

  The payload must be in JSON format.

  Click the Map Schema button to open the Schema Mapper.

  Use this screen to connect the payload values to the AgilePoint process schema.

Default Value:

Message Content

Accepts Variables:

Yes

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Map OpenAI Response To App Schema / Map JSON Response To App Schema

Description:

Specifies where to store the response from OpenAI.

Allowed Values:

• Map OpenAI Response To App Schema – Select this option if you want to map the information from the OpenAI data model to your process schema.

  Click the Schema Mapping button to open the Schema Mapper.

  Use this screen to connect the response to the data model for your process.

• Map JSON Response To App Schema – Select this option if you want to map the information from the payload specified in the Output field on the System Instruction > Output tab to your process schema.

  The payload must be in JSON format.

  Click Map Response to open the Schema Mapper.

  Use this screen to connect the response to the data model for your process.

Default Value:

Map OpenAI Response To App Schema

Accepts Variables:

No

Limitations:

• On the System Instruction > Output tab, if you enter the payload in the Output field,, the Map JSON Response To App Schema option is enabled.
• Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Store Response JSON In This Variable

Description:

Specifies a variable to store the information from the LLM.

In the text field, specify a variable that accepts an alphanumeric string in JSON format.

Allowed Values:

A variable.

Format:

• String

Accepted:

• Letters
• Numbers
• Spaces
• Special characters

Default Value:

None

Accepts Variables:

Yes

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Store Response Content In This Variable (String)

Description:

Specifies a variable to store the content of the text output from the LLM.

Allowed Values:

A variable.

Format:

• String

Accepted:

• Letters
• Numbers
• Spaces
• Special characters

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Add Row

Function:

Adds a row to create a parsing action.

Action

Description:

Specifies the protocol to use for parsing the generated text output from the LLM.

The parsing actions execute in the order added in the field.

Allowed Values:

A protocol from the list.

Default Value:

None

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Input

Description:

Specifies a variable that stores the generated text output from the LLM.

You must specify the variable configured in the Store Response Content In This Variable field on the Response tab.

Allowed Values:

A variable.

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Results

Description:

Specifies a variable to store the result of the parsing action.

Allowed Values:

A variable.

Format:

• String

Accepted:

• Letters
• Numbers
• Spaces
• Special characters

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Settings

Description:

Shows the settings configured for the parsing action.

Allowed Values:

Read only.

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

On Fail

Description:

Specifies whether to skip the parsing action when an error occurs.

Allowed Values:

• Selected - Skips the parsing action when an error occurs and moves to the next action.
• Deselected - Pauses the parsing action when an error occurs, and stores the error message in a variable if specified in the Save Parsing Error Message in this Variable field.

Default Value:

Selected

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Delete

Function:

Deletes the selected row.

Edit (JSON Parsing)

Opens this Screen:

Chat Completion - Initiate Subprocess Configuration > Parsing > JSON Parsing screen

To Open this Field:

1. In the Action field, select JSON Parsing.

Function of this Screen:

Configures the JSON code snippet for parsing the generated text output.

Edit (Inline Function)

Opens this Screen:

Chat Completion - Initiate Subprocess Configuration > Parsing > Inline Functions

To Open this Field:

1. In the Action field, select Inline Function.

Function of this Screen:

Configures one or more inline functions to parse the chat completion result.

Edit (Regex Parsing)

Opens this Screen:

Chat Completion - Initiate Subprocess Configuration > Parsing > Regular Expression

To Open this Field:

1. In the Action field, select Regex Parsing.

Function of this Screen:

Configures a regular expression for parsing the generated text output.

Save Parsing Status In This Variable (Boolean)

Description:

Specifies a variable to store the parsing status of the generated text output as a Boolean value.

The value is true if the prediction has no errors.

Allowed Values:

A variable.

Format:

• Boolean

Response Values

• true
• false

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (External) AI Control Towers & New Process Activities for Nvidia NIM

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Save Parsing Error Message In This Variable (String)

Description:

Specifies a variable to store the error message of the parsing action.

Allowed Values:

A variable.

Format:

• String

Accepted:

• Letters
• Numbers
• Spaces
• Special characters

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

JSON Path

Description:

Specifies a JSON code snippet to use for parsing the generated text output.

Allowed Values:

A JSON code snippet.

Default Value:

None

Accepts Variables:

No

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

JSON Input

Description:

Specifies a payload to use for parsing the generated text output.

Allowed Values:

A JSON code snippet.

Default Value:

None

Accepts Variables:

No

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Store JSON Parsing Result In This Variable

Description:

Specifies a variable to store the result of the JSON parsing from the LLM.

Allowed Values:

A variable.

Format:

• String

Accepted:

• Letters
• Numbers
• Spaces
• Special characters

Default Value:

None

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Skip JSON Parsing If Exception Occurs

Description:

Specifies whether to skip the parsing action when an error occurs in the AgilePoint NX app.

Allowed Values:

• Selected - Skips the parsing action when an error occurs, and shows an error in the log.
• Deselected - Shows an error in the log when an error occurs, but does not skip the parsing action.

Default Value:

Selected

Formula

Description:

Specifies the syntax of your formula.

Allowed Values:

An expression you build from the list of functions.

You can create a formula or expression using Text, Number, Currency, and Date functions from Inline Functions list, or process data variables.

To add more than one formula for your inline function, replace the text inside the parentheses ( ) of one function with a different function, in thise format:

@function1(@function2(variable1, variable2))

Default Value:

None

Example:

• @Max(Number1, Number2) - Gives the higher of the numbers represented by the varialbes Number1 and Number2.
• @UpperCase(SourceString) - Gives the text represented by the variable SourceString in capital letters.
• @UpperCase(@Substring(SourceString, StartIndex, EndIndex)) - Gives the specified substring of the text represnted by the SourString variable in capital letters.

Also refer to:

• (Example) Create an Inline Function

Inline Functions

Description:

Specifies the Text, Number, Currency, and Date functions to use in the formula.

Allowed Values:

• Concat - Joins two or more specified text values into one string.
• Stringlen - Gives the number of characters in the specified text value.
• Replace - Replaces all the occurrences of a specified text value in the instance with another specified text value.
• Remove - Deletes all the characters in the instance that begin at a specified position and continue through the last position.
• Reverse - Reverses the order of the elements in the instance.
• UpperCase - Returns a copy of the specified text value in capital letters, using the casing rule of the specified culture.
• LowerCase - Returns a copy of the specified text value in small letters, using the casing rule of the specified culture.
• TitleCase - Returns the specified text value in title case, except for the words that are in all capital letters, which are considered to be acronyms.
• PadRight - Returns a new text value that left-aligns the characters in an instance by padding them on the right with a specified Unicode character, for a specified total length.
• PadLeft - Returns a new text value that right-aligns the characters in an instance by padding them on the left with a specified Unicode character, for a specified total length.
• Substring - Gets a substring from an instance. The substring starts at a specified character position and has a specified length.
• GUID - Returns a text value of the GUID instance in a specific format.
• Insert - Returns a new text value in which a specified text is inserted at a specified index position in the instance.
• Trim - Remove all leading and trailing white space characters from the specified text.
• XmlEncode - Returns the specified text with escape characters by adding slashes (/) to use in XML attributes.
• XmlDecode - Returns the specified text as literal XML code.
• Compare - Returns true if both the specified text values are the same. This function is case sensitive.
• CompareIgnoreCase - Returns true if both the specified text values are the same. This function is not case sensitive.
• Absolute - Returns the absolute value of a number.
• Max - Returns the larger number of the two specified numbers.
• Min - Returns the smaller number of the two specified numbers.
• Power - Returns the specified number increased to the specified power.
• Round - Rounds the decimal value to the nearest integral value.
• Subtraction - Returns the difference of the specified n numbers. This function subtracts all numbers from the first number.
• Sum - Returns the sum of the specified n numbers.
• Average - Returns the mean of the specified numbers.
• Multiple - Returns the product of the specified n numbers.
• Modulo - Returns the remainder of the two specified numbers.
• Percentage - Returns the percentage of the two specified numbers. Number1 represents current value and Number2 represents total value.
• ToDecimal - Returns a decimal number.
• ToDouble - Returns a double-precision floating-point number.
• ToFloat - Returns a single-precision floating-point number.
• ToLong - Returns a number to an equivalent 64-bit signed integer.
• Currency - Shows the currency values in the format that you specify. This function shows the currency values with no decimal numbers.
• Currency - Shows the currency values in the format that you specify. This function shows the currency values with a specified number of decimal places.
• DateDiffDays - Calculates the difference in days between the two dates.
• DateDiffHours - Calculates the difference in hours between the two dates.
• DateDiffMinutes - Calculates the difference in minutes between the two dates.
• DateDiffSeconds - Calculates the difference in seconds between the two dates.
• FormatDate - Shows the date-time value in the format that you specify.
• AddYears - Returns a new date that is result of addition of the specified number of years to the specified date value.
• AddMonths - Returns a new date that is result of addition of the specified number of months to the specified date value.
• AddDays - Returns a new date that is result of addition of the specified number of days to the specified date value.
• AddHours - Returns a new date that is result of addition of the specified number of hours to the specified date time value.
• AddMinutes - Returns a new date that is result of addition of the specified number of minutes to the specified date time value.
• AddSeconds - Returns a new date that is result of addition of the specified number of seconds to the specified date time value.
• AddMilliSeconds - Returns a new date that is result of addition of the specified number of milliseconds to the specified date time value.
• AddTicks - Returns a new date that is result of addition of the specified number of ticks to the specified date time value.
• ParseDateTime - Converts the specified string representation of a date and time into its date and time value with the specified date format.

Default Value:

None

Example:

Refer to:

• (Example) Create an Inline Function
• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Description

Function:

Specifies the details of the function.

Default Value:

Read only.

Skip Inline Function If Exception Occurs

Description:

Specifies whether to skip the parsing action when an error occurs in the AgilePoint NX app.

Allowed Values:

• Selected - Skips the parsing action when an error occurs, and shows an error in the log.
• Deselected - Shows an error in the log when an error occurs, but does not skip the parsing action.

Default Value:

Selected

Apply

Function:

Uses the configured formulas in your inline function.

Example:

Refer to:

• (Example) Create an Inline Function

Regex Syntax

Description:

Specifies the format for your regular expression.

• The Regular Expression activity uses .NET syntax for regular expressions.

  For more information, refer to Regular Expression Language - Quick Reference.

• To change the regular expression, double-click Regex Syntex, and change your expression.

Allowed Values:

A valid regular expression..

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (Example) Configure the Regular Expression Activity
• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Perform Regex Match On This Text

Description:

Lets you specify the text to evaluate with the regular expression.

Allowed Values:

More than one line of text.

Format:

• Plain text
• A variable
• A combination of text and variables

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Store Regex Parsing Result In This Variable

Description:

Specifies a variable to store the result of the Regex parsing from the LLM.

Allowed Values:

A variable.

Format:

• String

Accepted:

• Letters
• Numbers
• Spaces
• Special characters

Default Value:

None

Accepts Variables:

Yes

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Skip Regex Parsing If Exception Occurs

Description:

Specifies whether to skip the parsing action when an error occurs in the AgilePoint NX app.

Allowed Values:

• Selected - Skips the parsing action when an error occurs, and shows an error in the log.
• Deselected - Shows an error in the log when an error occurs, but does not skip the parsing action.

Default Value:

Selected

Subprocess

Description:

Specifies a subprocess to start when the specified conditions occur in the generated text output.

This field shows the list of subprocesses in AgilePoint NX.

Allowed Values:

A subprocess from the list.

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Ellipses

Opens this Screen:

Chat Completion - Initiate Subprocess Configuration > Additional Actions tab > Mapping Variables

To Open this Field:

1. In the Subprocess field, select a subprocess.

Function of this Screen:

Specifies how to map variables in a subprocess.

Start Subprocess

Description:

Specifies how frequently the subprocess runs based on the generated text output.

An event for a specified activity is configured on the Triggered Events tab. Each time this event occurs, the AI model creates a text output. When the prediction meets the configured criteria, the AI Control Tower can be configured to trigger a subprocess. If the activity associated with the subprocess-triggering event runs in a process loop (the activity executes more than one time during a process instance) this field determines whether to run the subprocess only the first time the event on the Triggered Events tab occurs (the first session), or to run it every time the event occurs (every session).

Allowed Values:

• Only On First Session - Starts the subprocess only the first time the triggering conditions occur.
• For All Sessions - Starts the subprocess every time the triggering conditions occur.

Default Value:

Only On First Session

Example:

Refer to:

• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Set Action Trigger Condition

Opens this Screen:

Chat Completion - Initiate Subprocess Configuration > Additional Actions tab > Set Action Trigger Condition

Function of this Screen:

Specifies the conditions to start a subprocess in AgilePoint NX.

Save Status In This Variable (Boolean)

Description:

Specifies a variable to store the status of the generated text output as a Boolean value.

The value is true if the prediction has no errors.

Allowed Values:

A variable.

Format:

• Boolean

Response Values

• true
• false

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Save Error Message In This Variable (String)

Description:

Specifies a variable to store the error message for image classification.

Allowed Values:

A variable.

Format:

• String

Accepted:

• Letters
• Numbers
• Spaces
• Special characters

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (External) AI Control Tower – Predictive AI Agents for Image Classification

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Suspend Process Instance If Exception Occurs

Description:

Specifies whether to move the process forward when an error occurs in the AgilePoint NX app.

Allowed Values:

• Selected - Pauses the process when an error occurs, and shows an error in the log.
• Deselected - Shows an error in the log when an error occurs, but does not pause the process.

Default Value:

Selected

Example:

Refer to:

• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

Enable Debug

Description:

Specifies whether to store the debugging information for the AI Control Tower activity in the debug log folder on the AgilePoint Server machine.

Allowed Values:

• Selected - Stores the runtime debugging information for the AI Control Tower activity in a debug log file.

  A debug log file is created for each process instance.

  For more information, refer to Where Are the AgilePoint NX OnPremises Logs?

• Deselected - Does not store the debugging information for the AI Control Tower activity.

Default Value:

Selected

Example:

Refer to:

• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

Share All Variables (Basic) / Copy All Variables (Advanced) / Map Specific Variables (Advanced)

Description:

Specifies whether the parent process shares or copies all the process data variables or only the selected variables with the subprocess.

Allowed Values:

• Share All Variables (Basic) - Shares all the process data variables from parent process to subprocess.
• Copy All Variables (Advanced) - Copies all the process data variables from parent process to subprocess.
• Map Specific Variables (Advanced) - Shares selected process data variables from parent process to subprocess.

  Click the Configure button to open the Analyze Image - Initiate Subprocess Configuration > Actions tab > Initial Attributes screen.

Default Value:

Share All Variables (Basic)

Limitations:

Some information about third-party integrations is outside the scope of the AgilePoint NX Product Documentation. It is the responsibility of the vendors who create and maintain these technologies to provide this information. This includes specific business use cases and examples; explanations for third-party concepts; details about the data models and input and output data formats for third-party technologies; and various types of IDs, URL patterns, connection string formats, or other technical information that is specific to the third-party technologies. For more information, refer to Where Can I Find Information and Examples for Third-Party Integrations?

Attribute

Description:

A variable to connect with the subprocess.

Allowed Values:

A variable.

Default Value:

None

Value

Description:

The value in the subprocess to associate with the variable in the parent process.

Allowed Values:

A variable in the subprocess.

Default Value:

None

Accepts Variables:

Yes

Add

Function:

Adds a row.

Delete

Function:

Deletes the row.

Rule Type

Description:

Specifies a rule to execute.

Allowed Values:

• IF - Specifies a rule to execute if a specified condition is true.
• ELSE IF - Specifies a rule to execute if the previous condition is false.

  To open this field, click Add New Rule .

• ELSE - The rule executes if the all the specified conditions are false.

Default Value:

1. IF
2. ELSE

Rule Name

Description:

Specifies a name for a rule in your condition.

Allowed Values:

One line of text (a string).

Accepted:

• Letters
• Numbers
• Spaces

Default Value:

Rule Name 1

Edit

Opens this Screen:

Chat Completion - Initiate Subprocess Configuration > Actions tab > Condition Builder screen

Function of this Screen:

Creates or changes logical rules. You can put one statement inside another statement to create complex logical expressions.

Delete

Function:

Deletes the selected row.

Condition Name

Description:

Shows the name for your rule.

Allowed Values:

Read only.

Default Value:

Rule Name 1

Preview

Function:

Shows the preview of your rule.

Validate

Function:

Makes sure the rule is correct.

Rule Variable

Description:

Specifies the value to analyze.

Allowed Values:

One line of text (a string).

Accepted:

• Letters
• Numbers
• Spaces

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (Example) Configure a Condition Activity (Check Leave Approval Status)
• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

Operator

Description:

Lets you select the operators for a logical expression.

Allowed Values:

Data Type	Expression Operators
String	, ==, Starts with, Ends with, Contains, Does Not Contains, !=, Does Not Contain Data, Contains Data
Bool	==
Date Time	, ==, >, >= , <, <=, !=
Number	, ==, >, >=, <, <=, !=

Default Value:

None

Example:

Refer to:

• (Example) Configure a Condition Activity (Check Leave Approval Status)
• (Example) Configure a Condition Activity (Compare Leave Hours)
• (Example) Create Zoom Meeting

Rule Value

Description:

The value for the data variable.

Allowed Values:

One line of text (a string).

Accepted:

• Letters
• Numbers
• Spaces

Default Value:

None

Accepts Variables:

Yes

Example:

Refer to:

• (Example) Configure a Condition Activity (Check Leave Approval Status)
• (Example) Create Zoom Meeting
• (External) Supercharge Your end-to-end Orchestration with AI Control Tower: Real-Time Monitoring and Smart Decision Making

Add Row

Function:

Creates a condition row.

Select Nest Type

Function:

Specifies the use of logical AND and OR operators to nest conditions to use for predictions.

You must set the condition first, before you specify the nest type.

Allowed Values:

• And - Specifies the logical AND operator.
• Or - Specifies the logical OR operator.

Default Value:

AND

Indent Right

Function:

Creates the statement that is a condition of a parent statement.

Delete

Function:

Deletes the selected row.

Back

Function:

Saves the rule and goes back to the Create Condition screen.