Customer Kernel testing
Kernel testing involves taking a set of customer questions and searching their Expert site content to see if there are any relevant pieces of information (Kernels) that match. If the system finds relevant Kernels, the report will show where the answers would come from. If relevant Kernels are missing, this indicates a gap in the content that needs to be filled.
Perform a Kernel test
When gathering questions for Kernel testing, ensure that the questions accurately represent current user interactions and expectations. This allows you to create a comprehensive and representative set of questions for Kernel testing, ensuring a thorough evaluation of the ExpertAI system.
To formulate the initial set of 50 to 100 questions for testing:
- Leverage reporting data: Identify FAQs and common user interactions. This data-driven approach ensures that questions are representative of real usage.
- Reflect user expectations: Formulate questions that align with how users interact with the content and their expectations. This helps assess the ability to meet user needs.
- Include future state questions: Incorporate questions that anticipate future needs and potential new topic areas. Forward thinking ensures the system adapts over time.
- Direct audience engagement: Work with colleagues or conduct surveys to gain valuable insights into the most-asked questions and common inbounds they handle.
- Review onboarding materials: Examine the materials provided to new onboards, including questions they are expected to answer, to identify foundational questions that are crucial for new users.