Workflows with Agents

Agents in JetAdmin can be used inside workflows to add decision-making and flexibility to structured automations.

How Agents Fit into Workflows

Workflows handle defined steps, while agents evaluate context and determine the next action during execution. This allows you to build multi-step processes that can adapt without relying on complex conditional logic.

Example: Processing Orders from Input

In this example, a user submits order details through the app, and a workflow uses an agent to process and store the data.

1

Add Input Components

Add the following to your app in JetAdmin:

• A multi-line text input (for order details)

• A button (e.g. “Process Order”)

2

Configure the Trigger

Set the button action to:

• Trigger a workflow

• Pass the text input as a parameter

Triggers

3

Build Workflow Steps

In the workflow canvas:

1. Agent: Process Input

   • Read the submitted text

   • Extract structured order data (e.g. name, items, quantity)

   • Clean and format the data

2. Create Record

   • Save the structured data into the Orders table

3. Send Email

   • Generate a confirmation message

   • Send it to the customer or internal team

4

Test the Workflow

Enter sample order data and click the button to verify:

• The agent correctly parses and structures the input

• The record is created in the database

• The email is generated and sent successfully

Why Use Agents in Workflows

Workflows provide structured execution, while agents introduce flexible decision-making.

Together, they enable automations that are both reliable and adaptable without requiring complex logic or extensive conditions.

Agent Chaining

In more advanced setups, multiple agents can work together.

You can create specialized agents for different tasks and use them as tools within a main agent. The main agent can then delegate specific responsibilities to sub-agents when needed.

Clear and focused instructions for each agent are essential to ensure reliable coordination.