AI Test Toolkit

AI features can dramatically improve user productivity—but only when they’re reliable. Since LLMs generate output based on probabilistic patterns, traditional rule-based testing approaches aren’t sufficient.

Testing helps ensure that AI features:

• Deliver accurate, relevant responses
• Respond consistently to similar user prompts
• Avoid producing harmful, biased, or inappropriate content

Without proper validation, AI-generated outputs can lead to user frustration, compliance risks, and brand damage.

Thus, the developer tool for Copilot in Business Central includes an AI test tool app that lets developers write and run data driven tests for AI features, to evaluate functionality and accuracy.

Features

With the tool you can

• Create and run test suites for testing your AI features
• Develop AL test cases and add these test cases to your test suites
• Assign json or yaml data files to test suites, as well as individual test cases, for efficient data driven test runs covering many test data input scenarios
• Export results for external evaluation in, e.g., Azure AI Foundry, or evaluate in AL test cases
• Track pass rate, duration, token usage and accuracy for each suite

Supported Editions:

Supported Countries:

All countries supported by Dynamics 365 Business Central.

Supported Languages: