# How To

This section is designed to help you quickly find clear, actionable guidance on how to use Flow Designer effectively.

Refer to the following page to know more:

• Configure Workflow Trigger
• Add an Agent for Intelligent Tasks
• Create Conditional Paths with If/Else
• Add a Loop to Process a List of Items
• Manage Data with the Variable Assigner
• Update an EKG using the Knowledge Component
• Connect to External Systems with an Integrator
• Configure Workflow Settings
• Test the Workflow
• Activate Workflow

# Configure Workflow Trigger

# Define the Start Node

Follow these steps to configure the trigger that will initiate your workflow:
A workflow begins with the Start Node. The Start Node is an essential component that defines how a workflow is initiated

• On the canvas, locate the default Start component and click the '+' icon to open its Configuration Panel.
• Within this panel, you must choose one of the following Trigger Types to initiate the workflow:
• Manual/API Trigger: Select this option to start the workflow on-demand from the Governance tab or programmatically via an API call. You can optionally define input variables (e.g., string, number, file, etc.) that must be provided during execution.

For example,

• Event-Driven Trigger: Select this option to have the workflow start automatically in response to a specific event. You must complete the required configurations for the selected event source (e.g., an Email Trigger will require a Connection and a Folder path).
• Once the trigger is configured, it is saved as the first component on the workflow canvas.

# Add an Agent for Intelligent Tasks

Follow these steps to incorporate an intelligent agent from the Expert Agent Studio into your workflow.

• Step 1: Add and Link the Component

  • Drag an Agent component from the Component Panel onto the canvas.
  • Create a visual edge by dragging from an output node of a preceding component to the input node of the Agent.

• Step 2: Configure the Agent

  • Click the Agent component to open its Configuration Panel.
  • Select the specific agent you wish to use from the dropdown menu.
  • If applicable, select the desired version of the agent.

• Step 3: Map Agent Inputs

  • In the input fields (e.g., query, context), map the required data from the outputs of previous components.

# Create Conditional Paths with If/Else

Use an If/Else component to introduce decision points in your workflow. Based on the values available during execution, the flow can continue down different branches.

• Step 1: Add and Link the Component
  • Drag the If/Else component from the "Flow Control" section of the Component Panel onto the canvas and link it to a preceding node.
• Step 2: Build the Condition
  • In the Configuration Panel, build your logical condition by defining the operands and operator:
    • First Operand: Select an output variable from a previous step (e.g., the status code from an API call, a classification result from an AI Agent).
    • Logical Operator: Choose an operator from the dropdown (e.g., equals, contains, is greater than).
    • Second Operand: Enter a static value (e.g., the string "Success") or map a dynamic value from another component's output.

You can expand your conditional logic by clicking the + Else If or + Add Condition buttons to create additional evaluation criteria:

• + Else If: This adds a new, mutually exclusive condition to the sequence. The workflow evaluates each condition in order (If, then Else If 1, then Else If 2, etc.) and executes the action for the first condition that is met. This is ideal for defining a hierarchy of rules.
• + Add Condition: This button adds an extra check to the current If or Else If statement. You can combine multiple criteria using AND or OR operators. The action for that branch will only execute if all combined conditions within that single statement are true (for an AND operator) or if at least one condition is true (for an OR operator).
  

  

• Step 3: Build the Conditional Paths
  • Add subsequent components to the separate True and False branches that extend from the If/Else component. This defines the unique sequence of actions the workflow will take depending on whether the condition is met.
    

    

# Add a Loop to Process a List of Items

Follow these steps to enable iterative processing over a collection of data, such as multiple files or database records.

• Step 1: Add and Link the Component
  Drag the Loop component from the "Flow Control" section onto the canvas and link it to a preceding node.
• Step 2: Configure the Loop Input
  In the Configuration Panel, map an array from a previous step to the mandatory Input field, labeled "List of Item(s)".
• Step 3: Set the Error Handling Action
  Select an option from the On Error Action dropdown. "Continue on Error" will allow the loop to proceed to the next item if one iteration fails, while other options will stop the entire workflow.
• Step 4: Define the Loop Body
  Referencing the Current Item: To process each item individually within these components, map their inputs to the currentItem variable (e.g., Loop → item).
  Referencing Index: You can also use the currentIndex variable to track the position of the item in the array.
• Step 5: Configure the Loop Output (Optional)
  In the Output field, you can define a context variable to store and pass the aggregated results of the loop's operations to subsequent components.
  

  

# Manage Data with the Variable Assigner

Use this component to set or modify variables dynamically during workflow execution.

Step 1: Create an Environment Variable
The Variable Assigner can only interact with variables that have already been created. You must first define an Environment Variable in the workflow's settings before using this component.
For detailed instructions, refer to the Environment Variable section.

Step 2: Add and Link the Component
Drag the Variable Assigner component from the Component Panel onto the canvas.
Create a visual edge from the output node of a preceding component to the input node of the Variable Assigner.

Step 3: Select an Environment Variable Label
Click the component to open its Configuration Panel.
In the Label field, select an existing Environment Variable from the dropdown.

Step 4: Map the Value
In the Value field, choose the data you want to assign—this can be mapped from a previous component's output or set as a static value.

Step 5: Select the Operation Type
Under the Operation setting, choose one of the following options:

• Overwrite: Replaces any existing value in the target variable.
• Append: Adds the new value to an existing array in the target variable.

# Update an EKG using the Knowledge Component

Use this component to ingest new information into an Enterprise Knowledge Garden (EKG) during the workflow.

Prerequisite: The target EKG must already exist and be in a Published state. Draft or Unpublished EKGs cannot be selected in this component.

• Step 1: Add and Link the Component

  • Drag the Knowledge Garden Update component from the Component Panel onto the canvas.
  • Create a visual edge by dragging from an output node of a preceding component to the input node of the Knowledge Garden Update component.

• Step 2: Configure the Update Operation

  • Click the component to open its Configuration Panel.
  • In the Choose Knowledge field, select the target Enterprise Knowledge Garden from the dropdown menu. Only existing KBs will appear in this list.
  • In the Input field, map the variable from a previous step that contains the files to be ingested.

• Step 3: Add Metadata and Tags (Optional)

  • To enrich the ingested documents, you can add structured metadata and tags:
    • In the Metadata section, click the + button to add key-value pairs (e.g., DocumentType: Invoice). The key field includes a dropdown that lists existing metadata keys previously used in the selected Knowledge Garden.
    • In the Tags section, add one or more tags to classify the documents.
  • This information improves searchability and filtering for retrieval-based agents that use this Knowledge Garden.

# Connect to External Systems with an Integrator

Integrator components connect your workflow to external systems, such as cloud storage or databases. You can use them to fetch input files, send data for processing, or store outputs.

To demonstrate a practical application of this, we'll use an Integrator in the following use case.

Use Case: Build an Expense Report Processing Workflow
In this use case, you'll learn how to create an Automated Workflow that retrieves receipt files from an S3 bucket, classifies each file using an Agent, and extracts relevant data from documents identified as receipts for an expense report. The goal is to help you build, test, and publish a complete automation pipeline in just a few minutes.

This use case illustrates a full-cycle integration pattern:
Download -> Extract -> Process -> Compare -> Store

Prerequisites:

• You have a pre-built and published Automation Agent capable of classifying documents.
• You have a pre-built and published Automation Agent capable of extracting data from receipts.

Step 1: Create the Automated Workflow Agent
First, you'll create the foundation for your workflow's logic and configurations. This agent will act as the container for all the components and steps in your process.

1. Navigate to the Expert Agent Studio module.
2. Click the + Build button in the top-right corner.
3. In the What would you like to create? dialog, select Automated Workflow.
4. In the Solution Details section, provide the following:
   • Name: Expense_Report_Workflow
   • Description: Classify and extract incoming receipts from S3
   • Visibility: Private
5. Click Create to launch the canvas and begin designing your workflow.

Step 2: Configure the Start Node
Next, you'll define how the workflow is triggered. This is the essential first step that determines how your process begins.

1. Click the Start node on the canvas.
2. Under How Should This Workflow Start?, choose Manual or API Trigger.
3. In the Input Variables section, define the following input:
   • Input Name: Input_Path
   • Data Type: Text
   • This input defines the folder path in the S3 bucket that the workflow will monitor.

Step 3: Declare Environment Variable for S3 Bucket
Before adding the S3 connector, you'll define an environment variable for the bucket name. This makes the bucket reference reusable across your workflow and ensures it's correctly picked up during execution.

1. Navigate to the top header and click the Settings icon.
2. In the Environment Variables section:
   • Click + Add Variable.
   • Label: Bucket_Name
   • Value: employee-receipts-bucket (replace with your actual bucket name). This variable will now be available for use in the S3 component configuration.

Step 4: Add an AWS S3 Download Connector
Now, you'll connect the workflow to Amazon S3 to retrieve the receipt files. This component handles the interaction with the external cloud storage service.

1. Click the + button after the Start node.
2. Select AWS S3 and set the Operation to Download.
3. In the Configuration Panel, set the following:
   • Connection: Choose a valid connection (e.g., S3_Finance_Connector).
   • Bucket Name: Select the Bucket_Name environment variable.
   • Path: Map to Input_Path (defined in the Start node).

Step 5: Add a Loop to Process Each File
Because the S3 connector can return multiple files, a loop is needed to perform the same set of actions on each one individually.

1. Click the + button after the AWS S3 Download component.
2. Select the Loop component.
3. In the Configuration Panel, configure the following:
   • Input Variable: Select AWS S3 → files.
   • On Error Action: Choose Continue on Error. This ensures that if one file fails to process, the loop will still proceed to the next file.

Step 6: Add a Classification Agent Inside the Loop
You'll use an Agent to determine whether each document is a receipt. Placing this component inside the loop ensures it runs for every file retrieved from S3.

1. Inside the Loop, click the + button.
2. Select the Receipt Classifier agent.
3. In the Configuration Panel, map the agent's input:
   • Input (Receipt): Map to Loop → item.
   • This ensures that each file is passed to the agent one at a time.

Step 7: Add Conditional Logic to Handle Receipts
Next, you'll branch the flow with an If/Else component. This allows your workflow to make a decision and take different actions based on the classification result.

1. Add an If/Else component after the classification agent.

2. In the Configuration Panel, set the Condition: Receipt Classifier -> Expense_type equals meal_receipt

3. In the True (If) branch (this path runs if the condition is met):

   • Add the Receipt Extraction agent.
   • Input: Map to Loop → item
   • This agent performs structured extraction from documents confirmed as receipts.

4. In the False (Else) branch (this path runs if the document is not a receipt):

   • Add the SQS Send Message component.
     • Connection: Select AWS_SQS_Alerts.
     • Queue URL: https://sqs.us-east-1.amazonaws.com/123456789012/NonreceiptsQueue (replace with your actual URL).
     • Message: Unclassified Receipt.
     • This sends a message to the configured AWS SQS queue if the document is not classified as a receipt.

Step 8: Test and Publish the Workflow
Finally, you'll validate the workflow to ensure correctness before publishing. Testing is a critical step to catch errors before the workflow is live.

1. Click Test in the top header.
2. If your workflow uses a Manual Trigger, you will be prompted to enter an input path.
3. After the test completes, click on any component to view its Inputs, Outputs, and Traces. This is the primary way to debug your workflow's logic.
4. Once the workflow behaves as expected, click Publish.

At this point, your workflow successfully automates the process of retrieving receipts, using Agents to classify and extract key data, and intelligently routing documents for further action.

# Configure Workflow Settings

Follow these steps to configure global settings for your workflow, such as environment variables and failure notifications.

Navigate to the Settings icon, located in the header of the canvas. A new window will appear, containing the following sections:

• Environment Variable
  • To manage reusable, editable data without altering your workflow's logic, navigate to the "Environment Variable" section and click the + icon to create a new variable that you intend to modify later in the flow. You must define the following:
    • Label: A unique name for the variable
    • Data type: The type of data the variable will hold - String, Number, Object, Array (string), Array (number), Array (object)
    • Value: An initial default value for the variable.

• Notification Settings
  • To receive a notification when an error occurs in the flow, turn the Flow Error Notification toggle ON.
  • Additional fields will appear where you must provide recipient details (e.g., email addresses, SQS Send Message).

# Test the Workflow

Follow these steps to validate your workflow's logic and data flow before publishing:

• From the header bar at the top of the canvas, click the Test button. The Test Panel will appear.
  • If your workflow starts with a Manual Trigger, you will be prompted to provide sample data for the input variables you defined. For file inputs, use the Browse file button to upload a document.
  • If your workflow uses an Automated Trigger, ensure a valid connection is configured. The trigger will attempt to simulate an incoming event using pre-configured settings.
• Click the Run button to simulate a full, end-to-end execution of the workflow.
• After the test completes, you can click on any component on the canvas to view its Input, Output, and Traces (detailed logs) in the results panel. This allows you to correct errors and retest iteratively

# Activate Workflow

After a workflow is published, it appears in the Governance tab but is "Inactive" by default. Follow these steps to make your published workflow live and operational.

• Navigate to the Governance section of the platform
• In the asset list, locate your published workflow.
• Click the ... (more options) menu on the right side of the workflow's row and select Settings.
• In the dialog that appears, check the Activate Agent box.
• Click Submit to save the change. The workflow's status will update to "Active," and it will now run whenever its configured trigger conditions are met.