Skip to main content

How mabl enhances your testing with AI

Molly Exten
  • Updated

Artificial intelligence is more than just a buzzword at mabl. It's built into the fabric of our product, helping you deliver a higher quality experience for your customers. This article outlines the primary AI techniques that mabl uses, the features that use these techniques, and articles for further reading. 

Generative AI

Generative AI is a type of artificial intelligence that can create new and contextually-appropriate content, such as text, images, or code, by learning the complex patterns of human language and more. Thanks to vast amounts of training data, generative AI can apply these patterns to new information and problems to assist in a variety of tasks, from content creation to complex problem-solving. 

In mabl, generative AI helps simplify the process of test creation and improves test resilience. For example, if you need to create a custom JavaScript snippet to handle a specific testing scenario in your app, you can create and iterate on your snippet using the AI Snippet Generator. And if your application undergoes significant changes, mabl uses a process called advanced auto-heal during test execution to interpret page meaning and ensure your tests interact with the correct elements.

If you want to incorporate other popular generative AI models into your mabl tests, you can use API steps in your browser, mobile, or API test. See the gen-ai folder in the mabl Postman collections GitHub repo for examples.

To learn more about the use of generative AI in mabl, check out the following articles:

Protecting customer data

mabl’s generative AI capabilities are built on top of Google Cloud’s enterprise AI tools. Neither mabl nor our service partner, Google Cloud, use customer data for training these models. If you have any concerns about the use of generative AI in mabl, please reach out to your customer success manager.

For more information about how mabl handles customer data, see the article on data encryption.

Probabilistic expert systems

Expert systems are a branch of artificial intelligence designed to replicate the decision-making skills of human experts through a comprehensive set of structure rules and knowledge bases. These systems can analyze complex data and offer informed solutions in various fields. 

mabl combines expert systems with probabilistic models derived from data to understand and adapt to changes in your application over time. For example, when interacting with page elements, mabl uses a process known as Intelligent Wait to ensure that the application is in the correct state before executing a step. This process results in faster and more reliable test execution in any environment.

To learn more about the use of expert systems in mabl, check out the following features: 

Unsupervised machine learning

Unsupervised machine learning works by finding hidden patterns and relationships in data such as test run times. By analyzing the inherent structure of data, unsupervised machine learning can group similar items together and highlight anomalies. 

This technique helps mabl surface insights about tests in your application. For example, the accessibility dashboard in mabl leverages clustering to summarize accessibility issues by application page, which helps you prioritize which issues to address first. On the insights page, unsupervised machine learning helps detect anomalies in page load times and test run times, which can help you catch potential regressions.

To learn more about the use of unsupervised machine learning, check out the following features:

Related articles