The Workflow Builder is a no-code interface that enables Admins to create Agentic Workflows for AI Agents without writing a single line of code. Each Workflow is built using modular blocks that define how the AI Agent should:

• Collect information from users
• Evaluate conditions
• Take actions across different systems
• Respond with the right information
• Or hand off to a human Agent when needed

TABLE OF CONTENTS

• Trigger Block
• Collect Info Block
• API Action Block
• Condition Path Block
• Custom Response Block
• Agent Handoff Block
• Workflows Versioning

Here’s a breakdown of the six key blocks available in the builder:

Trigger Block

What it does:
This is the starting point of any Workflow. It defines when the AI Agent should initiate a Workflow, based on user input.

How to use:
Click the Trigger block to open a configuration panel where you can enter natural language instructions. This is where you define phrases or expressions customers might use to trigger the Workflow.

You can optionally include real-world examples and business-specific terms to make the AI Agent more effective. For instance, in an e-commerce domain, users may use terms like:

• “Check RTO status” (Return to Origin)
  
  
• “COD order issue” (Cash on Delivery)
  
  
• “Where’s my tracking number?”
  
  
• “Exchange window expired?”
  
  

Providing these domain-specific examples helps the AI better recognize customer intent and respond accurately—especially for industries with nuanced workflows or unique vocabulary.

Best Practice: Use varied, natural-sounding examples that your customers actually say.

Note: A common misconception is that the Trigger block can act on system events (like conversation initiation or positive/negative feedback) or detect sentiment. It cannot. The Trigger block only responds to customer queries.

Collect Info Block

The collect info block allows you to gather specific information from the customer during an AI Agent conversation. The collected inputs can then be used to trigger API actions, evaluate conditions, update properties, or send personalized responses within the workflow.

For example, you can collect details such as a flight booking ID, registered email address, contact number, order ID, or any other relevant identifier required to complete a request.

You can collect and map the following types of input parameters:

• Contact property: Select from the default and custom contact properties available in your account.
• Ticket property: Select from the default and custom ticket properties available in your account.
• Custom value: Select this to store customer information in temporary workflow-scoped variables.

For each input collected, you can additionally define the data type, add a description, and decide if the input is mandatory or not.

Note: Collecting unique identifiers such as email and phone numbers from visitors may have a security impact.

To collect input parameter:

1. In the workflow editor, click Add block > Collect info.
   
2. Click Input parameter and select the required type (contact, ticket, or custom).
   
3. In the Description field, provide details on the input required.
   For example, if you collect an email address and the description states “Email address associated with the booking”, the AI Agent will prompt the customer to provide the email used for the booking.
   
4. From the Type drop-down, map the appropriate data type for the input:
   • Text: Collects free-form input such as names, addresses, or order IDs.
   • Number: Collects numeric values such as quantities, PIN codes, or ticket numbers.
   • List: If you define items in the description, the AI Agent will treat the response as text input. The description guides the user’s response but does not display selectable options.
   • Boolean: Collects a true/false response. This is rendered as plain text and not as a radio button or toggle.
5. Select the Required field to mark the input as mandatory or optional.
   • When set as mandatory, the AI Agent continues prompting the customer until the required information is provided.
   • When set to optional, the Agent attempts to collect the information but continues the workflow even if the customer does not respond.
6. Click Save.
   Once configured, the collected inputs can be used in subsequent blocks within the workflow to personalise responses, update records, or trigger actions.

Best Practice:

• Keep questions concise and relevant
• Make only essential fields mandatory to reduce friction
• Use terms your customers are familiar with (e.g., “tracking ID” vs. “shipment reference”)
  
  

API Action Block

What it does:
 This block connects your Workflow to external systems via APIs, so the AI can retrieve or send data.

Two parts to configuring this block:

1. Choose or Create API Action

• Select an existing API action from the dropdown

Note: API actions you've used across all Workflows will be available here to choose from

• Or, click Create new API action to configure a new one from scratch. Click here to learn more.

To create a new API:

• Enter a name
  
  
• Define input variables
  
  
• Configure the API URL, headers, auth, and body
  
  
• Test the response
  
  
• Define output variables to store and reuse later
  
  

Note: Once created, API actions are reusable across multiple Workflows.

2. Map collected inputs to API parameters

Map your collected variables (e.g., order ID, email) to the corresponding API fields.

Under Advanced preferences, you can enable Ask for confirmation. When turned on, the AI will confirm with the customer before performing any sensitive action—like canceling an order or changing a plan.

Best Practice:
Always test your API action during setup. Use confirmation toggles for high-impact operations.

Condition Path Block

The condition path block allows you to branch the workflow based on information collected earlier in the conversation or retrieved from an API. It evaluates defined criteria and routes the conversation through different logic paths.

You can use the block to define the following details in the workflow: 

• Set multiple conditions (e.g., if order status is “shipped”)
• Add an Else path as a fallback
• Use outputs from the API or collected variables in your logic

For example, after retrieving order details, you can check whether the item has shipped or whether the order qualifies for expedited processing. Based on the evaluation, the workflow can proceed with the appropriate next step.

Define condition rules

To define a conditional path, you must clearly define the condition type, the operator, and the value. Together, these elements determine how the workflow evaluates data and decides which path to follow. 

Condition types

You can configure conditions using the following properties:

• Contact property: Default properties (such as phone number, email, first name, last name) and custom contact properties configured in your account.
• Ticket/conversation property: Default properties (such as ticket ID or conversation ID) and custom ticket fields.
• Account property: Account-level properties such as configured Business Hours (default or custom).

List of operators

It specifies the comparison logic applied between the selected property or variable and the defined value. After selecting the condition type and operator, specify the value to complete the rule.

Example:
If Business Hours is Active, the workflow can route the conversation to a live agent. If the condition is not met, the workflow can proceed with an after-hours response.

Note: The available operators vary based on the selected condition type. For example, Business Hours supports only Is and Is not, while text-based properties support additional comparison operators.

To add a conditional path:

1. In the workflow editor, click Add block > Conditional path.
   
2. Select the condition/property type and corresponding property. For example, contact Account properties > Business Hours.
   
3. Choose the appropriate operator and define the value.
   
4. Add additional conditions if required, and choose whether to meet all or any of the defined conditions.
5. Click Save.
   
   

Best Practice:

• Keep each path focused and purposeful
  
  
• Add fallback paths for incomplete or unexpected responses
  
  

Custom Response Block

What it does:
This block allows you to manually define how the AI should respond to the customer.

You have two options to set up your responses:

• AI-generated response - Use when the reply depends on customer inputs or fetched data (e.g., “Your flight from {origin} to {destination} departs at {time}”). Saves time and ensures dynamic accuracy.
  
  
• Send your own response - Use when the reply must always stay the same (e.g., “Please contact support for booking changes”). Good for policies, disclaimers, or standard instructions.
  
  

Best Practice:
 Use Custom Responses when tone, brand voice, or exact phrasing matters.

Agent Handoff Block

What it does:
 This block transfers the conversation to a live human agent when needed.

This is useful in:

• A workflow or specific condition requires handing the conversation over to agents
  
  
• When AI can’t resolve the query
  
  

Best Practice:
 Use this block at points of failure or uncertainty. Also, set expectations with a message like:

“I’m connecting you with a human agent who can help further.”

Workflows Versioning

Workflows versioning helps you make changes to existing Workflows quickly without having to disrupt or delete the active or live Workflow.

To make changes to an existing workflow,

1. On the Workflows list page, under Created Workflows tab, click on a Workflow you want to make changes to

2. Click Edit Workflow on the top right.

3. In the confirmation pop-up that discusses which AI Agents are using the Workflow, click 'Yes' and proceed to edit. 

4. A draft of the active Workflow will be created, where you can  make the changes required (for example: Changing a condition), ensuring the current active Workflow remains as-is
5. You can preview the changes you have made by clicking Preview Workflow at the top. Here you can test the Workflow to check if the changes you have made are now reflected. 

6. Once the changes are made, click Make it active
7. In the confirmation pop-up that appears, click Yes, Make it active. 

8. When you make a draft version active:
   1. The draft version will replace the current active version in both the Workflows library and AI agents
   2.  The previous active version will be removed
9. If you have a draft version that you haven’t made active yet. You will see the active and draft versions in the Workflows list view.

Note:
1) Workflow versioning is applicable only to custom Workflows.
2) Once the draft version is made active, all AI agents using the Workflow will use the new active version.