Prediction - Adapt Flow (MS Azure Machine Learning) activity

An activity that creates predictions created from data provided from an AgilePoint NX app to Microsoft Azure Machine Learning. If conditions configured in the AI model occur in the prediction, it can roll back or roll forward a process to a different activity.

This feature is part of the AI Control Tower.


Prediction Adapt Flow

Configure the Prediction - Adapt Flow activity

Examples

Prerequisites

Good to Know

How to Start

  1. Open Process Builder.

    For information about how to open this screen, refer to Process Builder.


    Open Process Builder
  2. In Process Builder, in the Activity Library, open the MS Azure Machine Learning tab.

    Amazon SageMaker tab
  3. On the MS Azure Machine Learning tab, drag the Prediction - Adapt Flow activity onto your process.

    Drag Prediction Adapt Flow activity

General Configuration

Specifies the basic settings for the Prediction - Adapt Flow activity.

Figure: General Configuration screen

General Configuration screen

Good to Know

  • Documentation for this screen is provided for completeness. The fields are mostly self-explanatory.

Fields

Field NameDefinition

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

Prediction - Adapt Flow Configuration > MS Azure Machine Learning tab

Configures the Microsoft Azure Machine Learning model to use to create predictions.

Figure: Prediction - Adapt Flow Configuration > MS Azure Machine Learning tab

Prediction Adapt Flow Configuration MS Azure Machine Learning tab tab

Fields

Field NameDefinition

Add Model Add Token icon
Function:
Creates a model with a name you specify.

In this activity, you can create more than one model to configure an Microsoft Azure Machine Learning model to give predictions for an app. Each configuration is stored as a model with a name specified in this field.

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?

Clone Clone Icon
Function:
Creates a new model that is a copy of the selected model.

Edit Edit icon

Function:
Changes the model name.

Delete Delete icon

Function:
Deletes the selected model.

MS Azure Machine Learning
Description:
Specifies the access token that connects to your Microsoft Azure Machine Learning service.
Allowed Values:
A list of access tokens configured for your environment.
Default Value:
None
Accepts Variables:
No
Example:
Refer to:

MS Azure Machine Learning
Opens this Screen:
Access Token for Microsoft Azure Machine Learning
Function of this Screen:
Configure an access token to connect to Microsoft Azure Machine Learning.

Save
Opens this Screen:
Saves the configuration for your model and does not close the configuration screen.

Prediction - Adapt Flow Configuration > Triggering Event tab

Configures an activity on which to run the Microsoft Azure Machine Learning model.

Figure: Prediction - Adapt Flow Configuration > Triggering Event tab

Prediction Adapt Flow Configuration Triggering Event tab

Fields

Field NameDefinition

Activity
Description:
Specifies an activity on which to run the Microsoft Azure Machine Learning model.
Allowed Values:
An activity from the list.
Default Value:
None
Accepts Variables:
No

On Event
Description:
Specifies the status for an activity instance where the change occurs.
Allowed Values:
  • Assign Work Item - Microsoft Azure Machine Learning runs when the specified task is ready to be Assigned to a participant .
  • Complete Work Item - Microsoft Azure Machine Learning runs when a task is Completed.
  • Cancel Work Item - Microsoft Azure Machine Learning runs when a task is Cancelled.
  • Enter Activity Instance - Microsoft Azure Machine Learning runs when the activity instance starts.
  • Leave Activity Instance - Microsoft Azure Machine Learning runs when the activity instance ends.
  • Reassign Work Item - Microsoft Azure Machine Learning runs when a task is Reassigned.
  • Work Item Assigned - Microsoft Azure Machine Learning runs after the specified task is Assigned to a participant.
  • Work Item Overdue - Microsoft Azure Machine Learning runs when a task is Overdue.
Default Value:
None

Set Trigger Condition
Opens this Screen:
Prediction - Adapt Flow Configuration > Triggering Event tab > Set Trigger Condition
Function of this Screen:
Specifies the conditions that cause the Microsoft Azure Machine Learning model to run.

Prediction - Adapt Flow Configuration > Triggering Event tab > Set Trigger Condition

Specifies the conditions that cause the Microsoft Azure Machine Learning model to run.

Figure: Prediction - Adapt Flow Configuration > Triggering Event tab > Set Trigger Condition screen

Prediction Adapt Flow Configuration Triggering Event Tab Set Trigger Condition screen

Fields

Field NameDefinition

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 Add New Rule icon.

  • ELSE - The rule executes if the all the specified conditions are false.
Default Value:
  1. IF
  2. ELSE

Condition
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 Edit icon
Opens this Screen:
Prediction - Adapt Flow Configuration > Triggering Event 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 Delete icon

Function:
Deletes the selected row.

Prediction - Adapt Flow Configuration > Triggering Event tab > Condition Builder screen

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

Figure: Prediction - Adapt Flow Configuration > Triggering Event tab > Condition Builder screen

Triggering Event tab Condition Builder screen

Fields

Field NameDefinition

Condition Name
Description:
Shows the name for your rule.
Allowed Values:
Read only.
Default Value:
Rule Name 1

Preview Preview icon

Function:
Shows the preview of your rule.

Validate Validate icon

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:

Operator
Description:
Lets you select the operators for a logical expression.
Allowed Values:
Data TypeExpression 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:

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:

Add Row Add Row icon

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 Indent Right icon

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

Delete Delete icon

Function:
Deletes the selected row.

Back Back icon

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

Prediction - Adapt Flow Configuration > Request tab

Specifies how to connect the request data from Microsoft Azure Machine Learning to the AgilePoint process schema.

Figure: Prediction - Adapt Flow Configuration > Request tab

Prediction Adapt Flow Configuration Request tab

Fields

Field NameDefinition

Map Request To App Schema / Enter Sample Request Payload / Read Payload From This Variable
Description:
Specifies how to connect the request data from Microsoft Azure Machine Learning to the AgilePoint process schema.
Allowed Values:
  • Map Request To App Schema - Connects the Microsoft Azure Machine Learning API request parameter to your process schema.

    Click Map Request To App Schema to open the Schema Mapper.

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

  • Enter Sample Request Payload - 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.

  • Read Payload From This Variable - Specifies a variable that stores the payload. The value of the process data variable must be in a valid JSON format.
Default Value:
Map Request To App Schema
Accepts Variables:
Yes
Example:
Refer to:
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?

Request Mapping
Description:
Connects the Microsoft Azure Machine Learning request to the process schema.
To Open this Field:
  1. Select Map Request To App Schema.
Allowed Values:
Click the Schema Mapping Schema Mapping icon button to open the Schema Mapper screen.

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

Default Value:
None
Example:
Refer to:

Prediction - Adapt Flow Configuration > Response tab

Specifies where to store the response from Microsoft Azure Machine Learning.

Figure: Prediction - Adapt Flow Configuration > Response tab

Prediction Adapt Flow Configuration Response tab

Fields

Field NameDefinition

Map Response To App Schema / Enter Sample Response Payload / Store Response In This Variable
Description:
Specifies where to store the response from Microsoft Azure Machine Learning.
Allowed Values:
  • Map Response To App Schema – Select this option if you want to map the information from the Microsoft Azure Machine Learning data model to your process schema.

    Click the Schema Mapping Schema Mapping icon button to open the Schema Mapper.

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

  • Enter Sample Response Payload - Specifies a payload to use to map the response to the AgilePoint 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.

  • Store Response In This Variable – Select this option if you want to store the information from Microsoft Azure Machine Learning to a variable in the AgilePoint NX app.

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

Default Value:
Map Response To App Schema
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?

Prediction - Adapt Flow Configuration > Additional Actions tab

Specifies variables to store the status of the Microsoft Azure Machine Learning model and to store the error message if an error occurs in Microsoft Azure Machine Learning. It also configures what to do when an error occurs in the AgilePoint NX app.

You can set conditions to change the flow of a process.

Figure: Prediction - Adapt Flow Configuration > Additional Actions tab

Prediction Adapt Flow Configuration Additional Actions tab

Fields

Field NameDefinition

Set Action Trigger Condition
Opens this Screen:
Prediction - Adapt Flow Configuration > Additional Actions tab > Set Action Trigger Condition
Function of this Screen:
Specifies the conditions to roll back or roll forward a process to a different activity.

Save Status In This Variable (Boolean)
Description:
Specifies a variable to store the status 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:
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 of the prediction.
Allowed Values:
A variable.

Format:

  • String

Accepted:

  • Letters
  • Numbers
  • Spaces
  • Special characters
Default Value:
None
Accepts Variables:
Yes
Example:
Refer to:
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:

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:
Default Value:
Selected
Example:
Refer to:

Prediction - Adapt Flow Configuration > Additional Actions tab > Set Action Trigger Condition

Specifies the conditions to roll back or roll forward a process to a different activity.

Figure: Prediction - Adapt Flow Configuration > Additional Actions tab > Set Action Trigger Condition screen

Prediction Adapt Flow Configuration Additional Actions tab Set Action Trigger Condition screen

Fields

Field NameDefinition

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 Add New Rule icon.

  • ELSE - The rule executes if the all the specified conditions are false.
Default Value:
  1. IF
  2. ELSE

Condition
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

Change Flow
Description:
Specifies the target activity to which to change the flow when the specified conditions occur.

This field shows the activities in the AgilePoint NX app.

Allowed Values:
An activity from the list.
Default Value:
Deselected
Example:
Refer to:

Edit Edit icon
Opens this Screen:
Prediction - Adapt Flow Configuration > Additional 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 Delete icon

Function:
Deletes the selected row.

Add New Rule Add New Rule icon

Function:
Lets you to add more than one rule.

Prediction - Adapt Flow Configuration > Additional Actions tab > Condition Builder screen

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

Figure: Prediction - Adapt Flow Configuration > Additional Actions tab > Condition Builder screen

Prediction Adapt Flow Configuration Additional Actions Condition Builder screen

Fields

Field NameDefinition

Condition Name
Description:
Shows the name for your rule.
Allowed Values:
Read only.
Default Value:
Rule Name 1

Validate Validate icon

Function:
Makes sure the rule is correct.

Preview Preview icon

Function:
Shows the preview of your rule.

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:

Operator
Description:
Lets you select the operators for a logical expression.
Allowed Values:
Data TypeExpression 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:

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:

Add Row Add Row icon

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 Indent Right icon

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

Delete Delete icon

Function:
Deletes the selected row.

Back Back icon

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