Amazon SageMaker activity

An activity that gives predictions based on an Amazon SageMaker model for the AgilePoint NX app. You can also skip activities in a process if the conditions specified in the Amazon SageMaker model occur.

Amazon SageMaker analyzes data in an app to make predictions. For example, if an app accepts data for college admission that has grades, course history, and other relevant data, Amazon SageMaker can predict whether the candidate qualifies for admission to a school.


Amazon SageMaker activity

Configure the Amazon SageMaker activity

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 Machine Learning tab.

    Open Machine Learning tab
  3. On the Machine Learning tab, drag the Amazon SageMaker activity onto your process.

    Drag Amazon SageMaker activity

General Configuration

Specifies the basic settings for the Amazon SageMaker 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

Function:
Specifies the activity name that shows in your process.
Accepted Values:
One line of text that can have spaces.
Default Value:
None
Accepts Process Data 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

Function:
Specifies an optional text description for your activity.
Accepted Values:
More than one line of text.
Default Value:
None
Accepts Process Data Variables:
No

Amazon SageMaker Configuration > Request tab

Configures the models for an activity where the Amazon SageMaker model runs.

Figure: Amazon SageMaker Configuration > Request tab

Amazon SageMaker Configuration Request 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 Amazon SageMaker 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?

Edit Edit icon

Function:
Changes the model name.

Delete Delete icon

Function:
Deletes the selected model.

Amazon Web Services

Opens this Screen:
Access Token for Amazon Web Services
Function of this Screen:
Configure an access token to connect to Amazon Web Services.

Create Add Token icon

Opens this Screen:
Access Token for Amazon Web Services
Function of this Screen:
Configure an access token to connect to Amazon Web Services.

Endpoint

Function:
Specifies the Amazon SageMaker endpoint to use for predictions.
Accepted Values:
An endpoint from the list.

When you select the access token from the Amazon Web Service field, this field shows the endpoints associated with the access token.

Default Value:
None
Accepts Process Data 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?

Target Container Host Name

Function:
Specifies the host name of the target container to use for predictions.
Accepted Values:
One line of text (a string) that can have letters and numbers, and can not have spaces or special characters. Hyphens (-) are accepted.
Default Value:
None
Accepts Process Data Variables:
Yes
Example:
AmazonSagemaker-02101989

Target Model

Function:
Specifies the name of the target model from Amazon SageMaker to use for predictions.
Accepted Values:
A target model from the list.

When you select the endpoint from the Endpoint field, this field shows the target model names associated with the endpoint.

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

Function:
Specifies an activity on which to run the Amazon SageMaker model.
Accepted Values:
An activity from the list.
Default Value:
None
Accepts Process Data Variables:
No

On Event

Function:
Specifies the status for an activity instance where the change occurs.
Accepted Values:
  • Assign Work Item - Amazon SageMaker runs when the specified task is ready to be Assigned to a participant.
  • Complete Work Item - Amazon SageMaker runs when a task is Completed.
  • Cancel Work Item - Amazon SageMaker runs when a task is Cancelled.
  • Enter Activity Instance - Amazon SageMaker runs when the activity instance starts.
  • Leave Activity Instance - Amazon SageMaker runs when the activity instance ends.
  • Reassign Work Item - Amazon SageMaker runs when a task is Reassigned.
  • Work Item Assigned - Amazon SageMaker runs after the specified task is Assigned to a participant.
  • Work Item Overdue - Amazon SageMaker runs when a task is Overdue.
Default Value:
None

Content Type

Function:
Specifies the format to send the request.
Accepted Values:
  • CSV
  • JSON
Default Value:
None
Accepts Process Data Variables:
No

Configure Request Mapping

Opens this Screen:
Amazon SageMaker Configuration > Configure Request Mapping
To Open this Field:
  1. On the Amazon SageMaker Configuration > Request tab, click Configure Request Mapping.
Function of this Screen:
Specifies the conditions that cause the process to skip activities.

Save

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

Amazon SageMaker Configuration > Configure Request Mapping

Configures the request in Amazon SageMaker.

Figure: Amazon SageMaker Configuration > Configure Request Mapping

Amazon SageMaker Configuration Configure Request Mapping

Fields

Field NameDefinition

Read Message From This Variable / Map Payload To App Schema / Map Payload To Grid

Function:
Specifies how to connect the request data from Amazon SageMaker to your AgilePoint process schema.
Accepted Values:
  • Read Payload From This Variable - Sends a request with a variable in the AgilePoint NX app.

    In the text field, specify a variable that stores the request.

  • Map Payload To App Schema - Connects the values in your payload with your process schema.

    Click Map Schema button to open the Schema Mapper screen. Use this screen to connect the values in the payload to your AgilePoint process schema.

  • Map Payload To Grid - Sends a request in specified key-value pairs.
Default Value:
Read Payload From This Variable
Accepts Process Data 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?

Column Name

Function:
Specifies the name of the column to use for predictions.
To Open this Field:
  1. On the Configure Request Mapping screen, select Map Payload To Grid.
Accepted Values:
A column name from Amazon SageMaker.
Default Value:
None
Accepts Process Data Variables:
No
Example:
CustomerName

Column Value

Function:
Specifies a value for the column in a key-value pair.
To Open this Field:
  1. On the Configure Request Mapping screen, select Map Payload To Grid.
Accepted Values:
A number or a text string that can contain spaces.
Default Value:
None
Accepts Process Data Variables:
Yes

Create Create icon

Function:
Adds a row for the Column Name and Column Value.
To Open this Field:
  1. On the Configure Request Mapping screen, select Map Payload To Grid.

Delete Delete icon

Function:
Deletes the selected row.
To Open this Field:
  1. On the Configure Request Mapping screen, select Map Payload To Grid.

Amazon SageMaker Configuration > Response tab

Specifies where to store the response from Amazon SageMaker.

Figure: Amazon SageMaker Configuration > Response tab

Amazon SageMaker Configuration Response 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 Amazon SageMaker 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?

Edit Edit icon

Function:
Changes the model name.

Delete Delete icon

Function:
Deletes the selected model.

Amazon Web Services

Opens this Screen:
Access Token for Amazon Web Services
Function of this Screen:
Configure an access token to connect to Amazon Web Services.

Create Add Token icon

Opens this Screen:
Access Token for Amazon Web Services
Function of this Screen:
Configure an access token to connect to Amazon Web Services.

Endpoint

Function:
Specifies the Amazon SageMaker endpoint to use for predictions.
Accepted Values:
An endpoint from the list.

When you select the access token from the Amazon Web Service field, this field shows the endpoints associated with the access token.

Default Value:
None
Accepts Process Data 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?

Target Container Host Name

Function:
Specifies the host name of the target container to use for predictions.
Accepted Values:
One line of text (a string) that can have letters and numbers, and can not have spaces or special characters. Hyphens (-) are accepted.
Default Value:
None
Accepts Process Data Variables:
Yes
Example:
AmazonSagemaker-02101989

Target Model

Function:
Specifies the name of the target model from Amazon SageMaker to use for predictions.
Accepted Values:
A target model from the list.

When you select the endpoint from the Endpoint field, this field shows the target model names associated with the endpoint.

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

Function:
Specifies an activity on which to run the Amazon SageMaker model.
Accepted Values:
An activity from the list.
Default Value:
None
Accepts Process Data Variables:
No

On Event

Function:
Specifies the status for an activity instance where the change occurs.
Accepted Values:
  • Assign Work Item - Amazon SageMaker runs when the specified task is ready to be Assigned to a participant.
  • Complete Work Item - Amazon SageMaker runs when a task is Completed.
  • Cancel Work Item - Amazon SageMaker runs when a task is Cancelled.
  • Enter Activity Instance - Amazon SageMaker runs when the activity instance starts.
  • Leave Activity Instance - Amazon SageMaker runs when the activity instance ends.
  • Reassign Work Item - Amazon SageMaker runs when a task is Reassigned.
  • Work Item Assigned - Amazon SageMaker runs after the specified task is Assigned to a participant.
  • Work Item Overdue - Amazon SageMaker runs when a task is Overdue.
Default Value:
None

Map Response To App Schema / Store Response In This Variable

Function:
Specifies where to store the response from Amazon SageMaker.
Accepted Values:
  • Map Response To App SchemaSelect this option if you want to map the information from the Amazon SageMaker 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.

  • Store Response In This VariableSelect this option if you want to store the information from Amazon SageMaker 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 Process Data 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?

Save

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

Amazon SageMaker Configuration > Additional Actions tab

Specifies whether to skip the activities in the AgilePoint process when specified conditions occur.

Figure: Amazon SageMaker Configuration > Additional Actions tab

Amazon SageMaker Configuration Additional Actions 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 Amazon SageMaker 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?

Edit Edit icon

Function:
Changes the model name.

Delete Delete icon

Function:
Deletes the selected model.

Amazon Web Services

Opens this Screen:
Access Token for Amazon Web Services
Function of this Screen:
Configure an access token to connect to Amazon Web Services.

Create Add Token icon

Opens this Screen:
Access Token for Amazon Web Services
Function of this Screen:
Configure an access token to connect to Amazon Web Services.

Endpoint

Function:
Specifies the Amazon SageMaker endpoint to use for predictions.
Accepted Values:
An endpoint from the list.

When you select the access token from the Amazon Web Service field, this field shows the endpoints associated with the access token.

Default Value:
None
Accepts Process Data 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?

Target Container Host Name

Function:
Specifies the host name of the target container to use for predictions.
Accepted Values:
One line of text (a string) that can have letters and numbers, and can not have spaces or special characters. Hyphens (-) are accepted.
Default Value:
None
Accepts Process Data Variables:
Yes
Example:
AmazonSagemaker-02101989

Target Model

Function:
Specifies the name of the target model from Amazon SageMaker to use for predictions.
Accepted Values:
A target model from the list.

When you select the endpoint from the Endpoint field, this field shows the target model names associated with the endpoint.

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

Function:
Specifies an activity on which to run the Amazon SageMaker model.
Accepted Values:
An activity from the list.
Default Value:
None
Accepts Process Data Variables:
No

On Event

Function:
Specifies the status for an activity instance where the change occurs.
Accepted Values:
  • Assign Work Item - Amazon SageMaker runs when the specified task is ready to be Assigned to a participant.
  • Complete Work Item - Amazon SageMaker runs when a task is Completed.
  • Cancel Work Item - Amazon SageMaker runs when a task is Cancelled.
  • Enter Activity Instance - Amazon SageMaker runs when the activity instance starts.
  • Leave Activity Instance - Amazon SageMaker runs when the activity instance ends.
  • Reassign Work Item - Amazon SageMaker runs when a task is Reassigned.
  • Work Item Assigned - Amazon SageMaker runs after the specified task is Assigned to a participant.
  • Work Item Overdue - Amazon SageMaker runs when a task is Overdue.
Default Value:
None

Change Flow

Function:
Specifies whether to skip the specified activities in the process after specified conditions occur.
Accepted Values:
  • Selected - Skips the specified activities in the AgilePoint process.
  • Deselected - Follows the standard process flow, and does not skip any activities.
Default Value:
Deselected

Configure Conditions

Opens this Screen:
Amazon SageMaker Configuration > Create Conditions
To Open this Field:
  1. On the Additional Actions tab, click Change Flow.
Function of this Screen:
Specifies the conditions that cause the process to skip activities.

Suspend Process Instance If Exception Occurs

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

Save

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

Amazon SageMaker Configuration > Create Conditions

Specifies the conditions that cause the process to skip activities.

Figure: Amazon SageMaker Configuration > Create Conditions

Amazon SageMaker Configuration Create Conditions

Fields

Field NameDefinition

Rule Type

Function:
Specifies a rule to execute.
Accepted 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

Function:
Specifies a name for a rule in your condition.
Accepted Values:
One line of text that can have spaces.
Default Value:
Rule Name 1

Change Flow

Function:
Specifies the activity to skip in the AgilePoint process after specific conditions occur.

This field shows the activities in AgilePoint process.

Accepted Values:
An activity from the list.
Default Value:
Deselected

Add New Rule Add New Rule icon

Function:
Lets you to add more than one rule.

Edit Edit icon

Opens this Screen:
Amazon SageMaker Configuration > 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.

Amazon SageMaker Configuration > Condition Builder screen

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

Figure: Amazon SageMaker Configuration > Condition Builder screen

Amazon SageMaker Configuration Condition Builder screen

Fields

Field NameDefinition

Condition Name

Function:
Shows the name for your rule.
Accepted 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

Function:
Specifies the value to analyze.
Accepted Values:
One line of text that can have spaces.
Default Value:
None
Accepts Process Data Variables:
Yes
Example:
Refer to:

Operator

Function:
Lets you select the operators for a logical expression.
Accepted Values:
Data TypeExpression Operators

String

, ==, StartsWith, EndsWith, Contains, !=, Does Not Contain Data, Contains Data

Bool

==

Date Time

, ==, >, >= , <, <=, !=

Number

, ==, >, >=, <, <=, !=

Default Value:
None
Example:
Refer to:

Rule Value

Function:
The value for the data variable.
Accepted Values:
One line of text (a string).

Accepted:

  • Letters
  • Numbers
  • Spaces
Default Value:
None
Accepts Process Data Variables:
Yes
Example:
Refer to:

Add Row

Function:
Adds a row for the Field Name and Field Value.

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 your rule and goes back to the Create Condition screen.