How do you see yourself leaning towards AI in upcoming days?

As a QA, I see AI as a valuable support tool to improve the speed and accuracy of testing. I’m interested in using AI for areas like test case generation, identifying patterns in bugs, analyzing logs, and even helping prioritize what to test first.

 I've already built a POC using Copilot and Playwright MCP to explore webpages, generate test code, and self-heal locators. Moving forward, I plan to expand AI’s role in test generation, maintenance, and collaboration to drive smarter, faster, and more resilient testing.
 

I plan to lean further into AI by:

• Expanding autonomous test generation: Using GenAI to interpret requirements and user stories to create meaningful test scenarios.
• Enhancing test maintenance: Leveraging AI to predict flaky tests and proactively suggest fixes based on historical data.
• Improving collaboration: Using natural language interfaces to allow non-technical stakeholders to contribute to test creation.
• Integrating AI into CI/CD pipelines: Automating test data generation and environment setup using AI-driven tools.
• Continuously learning and adapting: Staying updated with advancements in GenAI and experimenting with new models and frameworks to push the boundaries of intelligent automation.

Unlike traditional software, LLM outputs can vary for the same input — so traditional QA methods (like checking expected vs actual) just aren’t enough. We’re living in the era of LLMs, and it's time QA evolves with it!

I see myself integrating AI throughout the QA lifecycle—using models to draft and refine test cases, uncover edge‑case scenarios, and dynamically prioritize and adjust test suites based on code changes; leveraging conversational agents in tools like Jira or TestRail for faster status updates; and feeding AI‑powered dashboards and narrative summaries to highlight trends and predict risks, so I can shift from manual tasks to strategic oversight, catch issues earlier, and communicate insights more efficiently.

I’m already using copilot in my everyday work.

In the upcoming days, I see myself increasingly leaning towards AI as both a tool and a partner in enhancing productivity, creativity, and decision-making. With AI rapidly evolving, I aim to integrate it into my daily workflow, whether it's automating repetitive tasks, gaining insights from data, or exploring new ways to solve complex problems. I’m particularly interested in learning how to collaborate with AI systems to augment my skills, stay ahead in my field, and contribute meaningfully to innovation. As AI becomes more accessible, I believe it will empower me to focus more on strategic thinking and less on routine execution.

Have already started using the open ai apis to generate the test cases ,test scenarios, synthetic test data , feature file and test script generation.created a plugin in jira to generate the cucumber feature file based on the user story .

Q:How to do you see yourself leaning towards AI in upcoming days?
My Response :
"I'm actively using AI to boost test coverage, auto-generate cases, and debug faster. I’m also building AI-assisted QA tools, integrating LLMs into CI pipelines, and learning prompt engineering to stay ahead. For me, AI isn’t just the future—it’s my present testing strategy."

Learning and doing AI Trends

AI is going to kill, especially MCP and Lang chain combination, Prompt based testing is the future. 

Hello ​@executeautomation ,

As a curious mind deeply passionate about innovation, I see myself not just leaning into AI but diving right into it. I think of AI not as a mere tool but as an equal partner that boosts my own creative powers, problem-solving skills, and approach toward challenges. From automating dull tasks to delving into generative AI for more clever ways of testing and development, I'm eager for the ride. To me, AI is not just the future; it is my compass for landing my learning, growth, and carving out meaningful impact in tech.

Thanks,

Ramanan 

I will try out the MCP server and especially the agent mode to setup a basic Playwright test set from scratch (basically ‘Vibe-testing’)

I believe the future of QA lies in embracing AI not as a replacement, but as a powerful augmentation to our capabilities. The role of a QA engineer is evolving — AI is transforming how we approach test case generation, defect prediction, and even dynamic test maintenance. But rather than eliminating our role, it's reshaping it. In my view, it's not AI that will replace QA engineers, but rather QA engineers who resist adapting to these AI-driven changes who may find themselves left behind.

The engineers who thrive in the future will be those who learn to work alongside AI — guiding it, validating its outputs, and using it to accelerate coverage, improve efficiency, and uncover patterns we might miss manually. Just like how automation didn't replace QA but redefined our skills, AI will do the same. So, the 'AI-augmented QA engineer' is not just a concept — it’s the new reality taking shape.

I plan to do a government funded apprenticeship with GenAI .But Practically implementing and learning through trial and error is the best way to keep up with the pace of ever evolving AI. I also think my understanding with AI would be augmented by implementing it tin my day to day job and being an advocate across the team. Attending webinars like these are real eye openers to understand industry trends and practices.My ambition is to use AI to enable QA efficiencies along with suatainability practices.

I will learn and adapt GenAi tools with utilizing its features and not completely depend on those tools. 

As a QA lead, i already started using company chat GPT for our project uses and saved time in many areas. I am more curious to use the AI tools and languages suggested by Karthik in this session and implement in my project to work towards more innovations which will benefit my clients and company.

I see myself increasingly leaning towards AI in the coming days as it continues to transform how we solve problems, make decisions, and improve efficiency. I'm particularly interested in exploring how AI can be integrated into everyday tasks—be it in automation, data analysis, or even creative fields.

I plan to invest time in understanding how AI works under the hood, not just using it but also learning how to build and fine-tune AI models. Whether it's through hands-on projects, certifications, or collaborating on real-world use cases, I aim to be more than just a user—I want to be a contributor to meaningful AI-driven solutions

Yes, using the AI in my day to day QA activities will help me, but I will use AI with all my basics. We should not forget one thing , “We can not replace our Testing Activities (Manual/Automation) with AI, but we can use AI with it.

Thanks

I shall be using it as per many of the scenarios and use cases mentioned by Karthik. Most of the things like getting the help for R&D on the topic of interest like API testing, Meeting Recording script and get the action items from the meetings, and many other scenarios etc.

The AI capabilities that I use currently is for generating our own AI assistants to produce manual documentation,  perform Code reviews, work as a knowledge base through chat assistant enabling the team to interact with our internal knowledge base via a chat interface.

Exploring more on how to implement the AI on a codeless testing tool like Tricentis Tosca. Also how to use AI to report defects to Jira from our own test management tool, create test plans, generate manual test cases, etc.

I’ve already started using AI tools like GitHub Copilot and ChatGPT to assist with both Automation and Manual testing. Looking forward to upskilling the ways of using AI productively and following some course specifically designed for Test Engineers.

In the upcoming days, I see myself embracing AI as both a learning opportunity and a practical tool to enhance my skills and productivity. I’m particularly interested in understanding how AI can support industries like education, healthcare, and software testing. I plan to explore AI-powered tools to automate repetitive tasks, gain insights from data, and improve decision-making. I also look forward to upskilling myself through courses and hands-on projects in AI and machine learning so I can contribute meaningfully in any AI-integrated environment

AI is truly a game-changer in software testing and can significantly boost efficiency when used in the right direction. Here’s how I plan to integrate AI into my day-to-day testing workflows:

1.> Test Case Generation from Requirements

Example: Convert Jira ticket descriptions into Gherkin syntax for automated testing

2.> Test Data Generation

Example : Integrate with tools like ChatGPT to generate input data dynamically before test execution.

3.> Root Cause Analysis

Example : Use AI models trained on past test failures to predict flaky tests or environment issues.

4.> Visual Testing with AI

Example : Integrate with tools like Percy or Applitools in your CI pipeline for smarter UI regression detection

5.> Smart Test Prioritization

Example : Only execute high-risk or recently impacted tests post-deployment or after a pull request

6.> Setup Automatic code Review for PR raise and Integrate it with CI/CD

Example : Integrate a custom GPT agent or LLM with Stash to review automation code during PR creation

The task of writing test cases and automation of test is easier now with the LLMs. Hence, as tester we would now need to be one step ahead in order to verify if LLM is giving us the appropriate test case/code or should we improvise.

To be able to choose the best solution from available ones provided by LLM, our role is to make sure we understand what AI is doing and then leverage it to create a better quality software.

Inspired by The Singularity Is Near, I see AI not just as a tool, but as a transformative force — and I’m keen to adapt early and grow alongside it.