Automation V3: Image Validator

The AI Image Validator uses advanced AI-driven capabilities to verify images within your test cases. It allows users to input an image and automatically compares it against the expected visual intent, ensuring precise and reliable validation results.

This feature enhances Agentforce testing by supporting scenarios where images are included as part of the system response. With this addition, users can now perform image validation directly on any webpage. Additionally, the AI Image Validator provides flexibility by allowing users to download and validate images locally, enabling broader coverage across diverse testing workflows.

This Image Validator AI feature verifies images against a provided description using AI capabilities, supporting various image formats (jpg, jpeg, png, webp, and gif) up to 5MB and providing reasons for validation results, including flagging unsafe images.

Use Cases:

• Validate that a logo, icon, or banner renders correctly after a deployment.
• Confirm that specific UI components or visual states (e.g., buttons, error messages) match expected designs.
• Detects missing or incorrectly displayed images during end-to-end regression testing.

Step Settings:

Inputs:

Image Path (Text, Mandatory)
Provide the image via a URL or file path. You can search in using the browse folder next to the 

User Intent (Text, Mandatory)

Enter the text description the image should match. 

Result:

Result Name

Choose a name for the results to be stored locally for future use.

Result Scope

Select a scope to avoid data collisions in various testing scenarios by limiting the access of the Results Name variable.

General Parameters:

Continue on Failure (Checkbox)

If the box is unchecked, the test will stop running if the image does not match the intent. 

If the box is checked, the test will continue after reporting the failure.

Execute the Test

1. Run the test containing the Image Validator step. Provar performs the image validation using its hosted AI service.
2. Review the test execution results in the Test Output panel.

• Pass: The image matches the expected description as per defined criteria.
• Fail and Stop: The image does not meet the expected validation criteria and the test stops at this step.
• Fail and Continue: The image does not meet the expected validation criteria but the rest of the test case is run.

Review and Troubleshoot Results

If validation fails, check the following:

• The image file path or URL is valid and accessible.
• The image is a supported file type (jpg, jpeg, webp, png, gif) and does not exceed the size limitation (5MB).
• The description accurately represents the expected image.

---

Feedback

Was this article helpful for you?

We really appreciate it!

Thank you for your feedback.

Tell us how we can improve this article.

No Yes