Adha Hrusto

Adha Hrusto is an AI Engineer with a PhD in Computer Science, specializing in applying ML and GenAI to enhance software quality. Her experience spans research and industry, including the development of agentic AI chatbots and AI-driven test automation frameworks.

Her doctoral research focused on anomaly detection in DevOps, as part of Sweden’s largest research initiative (WASP). Adha has turned cutting-edge research into impactful real-world solutions, working closely with clients and sharing her results through publications and presentations at international conferences.

Therefore, she is passionate about sharing insights on how AI can shape innovation and meaningful change across modern development ecosystems.

This talk explores the transformative integration of AI into automated API testing. By leveraging advanced prompt engineering techniques and large language models, we generate test models in a predefined, structured format crafted to reflect both contract and system testing requirements from comprehensive business needs and OpenAPI specification. These models are then seamlessly transformed into executable test code through a templating mechanism, which guarantees consistency and reliability.

This powerful process leverages AI to explore a wide spectrum of tests while ensuring that the stability and quality of the final code remain intact. We will demonstrate this workflow through a practical example, showing how models are generated and converted into executable tests, and how this approach significantly accelerates test creation. The example will highlight how AI-driven generation enables both broader coverage and faster iteration without compromising quality. Attendees will leave with practical insights on transitioning from the traditional practice of coding tests to a modern approach focused on reviewing and refining AI-generated test files, setting the stage for a new era in software testing.

Key Takeaways:

• Structured Models: AI generates clear, structured test models.
• Templated Code: Models are transformed into robust, executable tests.
• New Paradigm: Shift from manual coding to strategic test review.