Automate dynamic workflows with AI interactions

Use natural language to perform dynamic actions and validations on your website.

Low Code Automation offers AI Interactions, a feature that lets you generate test steps using natural language prompts based on your website’s current state. Unlike traditional fixed steps that may break when your website changes, AI-generated steps dynamically adapt to the context during each test run.

For example, if you’re testing a flight booking flow and need to select today’s date, a fixed date selector might fail when the test is run on a different day. With AI Interactions, you can simply prompt: “Select today’s date for departure”, and the correct date will be automatically selected every time the test runs.

Example Use Cases:

• Enter any available date in the next month for departure and return dates: AI analyses the page, finds the next month, and selects any available date accordingly.
• Ensure terms and conditions are mentioned in English: The AI verifies that the terms are in English, based on the current page.
• Add to cart the first product from the search results having price greater than $20: The AI analyses the search results, identifies products priced over $20, and adds the first one to the cart.
• Validate search results are sorted in ascending order of price: The AI verifies the current page to confirm that the terms and conditions are written in English.

Generate dynamic test steps with AI interactions

1. In the Low Code Automation recorder, go to the step where you want to generate an interaction, then click AI interactions.
   
   
2. Select the type of action you want to perform:
   • Validation: Use validation to perform any type of dynamic validation which depends on the application state.
   • Action: You can use Action to perform any dynamic action on the website or extracting any dynamic text from the website
3. Enter the desired prompt.
   While actions or validations are being performed, you can also view the AI thoughts to understand what is AI thinking while performing the step. If a test step fails due to the prompt, review these thoughts to understand the issue and refine the prompt accordingly.
4. Click Validate or Perform.

AI Validation

The following is a sample use case that demonstrates how to add validation to using AI interaction.

Once the step execution finishes, it displays whether the validation passed or failed.

AI Action

The following is a sample use case that demonstrates how to generate test steps using AI interaction.

Supported actions for AI interactions

AI interactions support the following types of user actions:

• Click
• Text Input
• Hover
• Scroll up
• Scroll down

Edit AI steps

You can edit the step by modifying the prompt even after execution. Click Edit prompt below the AI interaction to update the prompt and regenerate the step.

The prompt window appears. You can edit the existing prompt or enter a new one.

Replay AI steps

The following is a sample use case that demonstrates execution of a step generated using AI interaction. Every time the step executes during replay, it uses AI based on the specified prompt.

AI Validation Replay

AI Action Replay

Points to remember

• AI Interactions is currently in Alpha and supports a maximum of 5 AI-generated steps per test.
• Use the recorder to create static steps—ideal for parts of your application that don’t change frequently.
• For dynamic workflows, use AI Interactions for actions and validations that adapt based on the application’s current state.
• AI Interactions work best for targeted, context-aware actions or validations. Ensure to use very specific prompts to generate more precise and accurate steps.
• Avoid writing prompts that require scanning across multiple pages or achieving large objectives. Instead, break tasks into smaller, focused actions or validations for better accuracy and reliability.
• Ensure you write concise and clear prompts and provide relevant context.