STARWEST 2024 - AI/ML | STARWEST

STARWEST 2024 - AI/ML

Wednesday, September 25

Dmitriy Gumeniuk
EPAM Systems
W1

The Rise of the Virtual QA Engineer: Harnessing GenAI

Wednesday, September 25, 2024 - 11:30am to 12:30pm

In this talk, Dmitriy will delve into the transformative journey of integrating GenAI, into the core of his team's testing and development processes. This integration has not only enhanced their productivity by 15% but also yielded a 20% time saving and a significant cost reduction per test case. Want to know how? The session will explore his team's strategic implementation of GenAI, overcoming security challenges, leveraging diverse (LLMs), and the meticulous design of prompts that culminated in a prompt library. See how tailored extensions for the code editors and corporate chats...

W7

Generative AI is Transforming Software Testing: What Testers Need to Know

Wednesday, September 25, 2024 - 1:30pm to 2:30pm

We have all seen it. The word AI is appearing next to every test tool, and the promises are coming thick and fast. AI seems like the perfect addition to increase the quality of the tests we run, but what if the opposite is true, and it’s the death of quality engineering as we know it? There has been no greater transformation in test quality than test automation in the last decade. We have gone through the horrible years of record and replay automation that never provided the ROI that was promised, and we finally settled on automation engineering, where we treat our automation code with the...

W13

Reinventing the Art of Software Testing with Google Cloud AI Platform

Wednesday, September 25, 2024 - 2:45pm to 3:45pm

This session explores the innovative ways to approach and revolutionize the art software testing by harnessing the full power of Google Cloud AI Platform. Utilizing AI-powered regression testing and natural language processing (NLP) capabilities, developers can automate mundane and repetitive tests while also analyzing software functionality and usability. Predictive analytics and custom machine learning models can be used to anticipate and identify potential issues, improve testing efficiency, and provide actionable insights. Applying reinforcement learning algorithms for GUI testing,...

Thursday, September 26

T1

Bridging AI-Generated Acceptance Criteria with Comprehensive Test Scenarios

Thursday, September 26, 2024 - 9:45am to 10:45am

The generation of acceptance criteria through generative AI is an innovative approach to streamline the requirements gathering process. However, ensuring that the implemented code aligns with these criteria is crucial for delivering high-quality software. This talk explores the integration of generative AI generating acceptance criteria with test case scenarios, aiming to establish a seamless connection between the development and testing phases. By leveraging pull requests as a central hub, this approach facilitates the validation of whether the test case scenarios adequately cover the...

Tim Heck
MRI Software
T7

“Low Code”—Coded Automation Using Free Tools

Thursday, September 26, 2024 - 11:15am to 12:15pm

Using artificial intelligence to generate test code is a hybrid automation strategy that combines the best of both worlds. Tests can be created very quickly by almost anyone using AI, yet the tests are still planned by humans and maintainable by humans. With the right prompts, you can have AI construct traditional test code using open source testing tools that the world is already familiar with (Chai, Mocha, Cypress). As a result, you end up with structured code that is logical and easy to maintain without having to wonder what the AI is testing. In this session, Timothy will look at...

SQALogic
T13

The Quality Assurance of Artificial Intelligence: How to Test the Tests!

Thursday, September 26, 2024 - 1:30pm to 2:30pm

Many companies are asking the question: "What can AI do to improve our QA practices?" But is this the right question? David believes that as QA practitioners the real question is "How should we be preparing to efficiently test emerging and complex ML an AI systems?" AI testing is different from traditional testing because AI systems are not static, but dynamic and adaptive. They learn from data and feedback, and change their behavior accordingly. This means that AI testing must account for the variability and unpredictability of AI systems, and ensure that they are not only functional, but...

Adam Sandman photo
Inflectra
T19

Multi-Modal GPTs Are Coming For Your Testing! How to Adapt?

Thursday, September 26, 2024 - 3:00pm to 4:00pm

As you research the latest in generative AI technology, you will see that the development and availability of multi-modal GPT engines are fundamentally changing the way applications are tested and described. These new GPT models can generate and interpret voice, text, and images seamlessly. For example, you can ask them to navigate an application to accomplish a business task and comment on their actions. This means that we’re for the first time entering the world of AI-assisted/performed exploratory testing. When you couple this with the capabilities of GPT models to identify UI elements...