Week 4 Exercise - From Learning to Leading – Be the Gen AI Ambassador of your team

​@Saravanan s congratulation on completion of all the exercises and sessions.

You will be receiving it soon. tagging ​@Mustafa for next steps and updates on this.

Thanks for your response

Hi Rahul, Greetings.

Even, I have not yet received the certification for the mini-course “Generative AI for Testers” by Rahul Parwal. Could you please check the status and provide an update? Many Thanks. Nitin

​@parwalrahul ​@Mustafa 

I also have the same query on certificate. Pretty excited and waiting for it.

Kusum

Hello, ​@Saravanan s, ​@Kusumketu  and ​@NitinMore 

We haven't sent the certificates yet. Make sure to finish Rahul's exercises and we will hand out the certificates this week.

Thank you, shiftsync team, for this wonderful webinar, and ​@parwalrahul for the valuable insights.

Looking forward to more such helpful content in today’s competitive world.

Key Learnings

• Fundamentals of Generative AI: Gained insights into how Gen AI models function, the role of domain-specific LLMs, and their inherent limitations in real-world applications.

• Gen AI Use Cases in Testing & RAG Concepts: Rahul’s presentation on leveraging Generative AI in testing was particularly insightful, especially the slide diagram illustrating practical applications in automation and Retrieval-Augmented Generation.

• Prompt Engineering for Testing: Learned techniques to craft effective prompts for AI-driven test case generation, test data creation, and API request formulation, enhancing testing efficiency.

• Generative AI: A Double-Edged Sword: Explored the advantages of AI across various domains while also understanding its risks, ethical concerns, and potential biases that need to be mitigated.

Key Tasks & Action Plan

• AI in Automation Testing: Plan to integrate AI-driven self-healing capabilities into my automation scripts, allowing tests to dynamically adapt to UI changes and reducing script maintenance overhead.

• AI in Manual Testing: Utilize AI tools to assist in generating manual test cases and evaluating their accuracy and relevance to real-world testing scenarios.

• AI in Continuous Testing: Research and implement AI-powered test insights within the CI/CD pipeline to automate regression and smoke testing, ensuring faster feedback loops and better test coverage.

• AI-Driven Test Data Strategy: Leverage AI to generate diverse test data sets, covering boundary values, edge cases, and performance test scenarios to improve test robustness and system reliability.

Great stuff ​@Charmi07 .

All the best with you plans! Congratulations on completing this course :)

Throughout this course, I’ve learned a lot about how Gen AI can revolutionize testing. One of the key takeaways is how AI can significantly speed up test automation by generating scripts and handling repetitive tasks that would otherwise take up a lot of time. Another important learning is how to create well-structured prompts to get more relevant and actionable results from AI, which is essential in making the most out of automation tools. Lastly, I’ve gained an understanding of how AI can help in test data generation, making it easier to simulate real-world scenarios for more accurate testing.

Looking ahead, I plan to use Gen AI in a few key tasks over the next three months. First, I will integrate it into the creation of automated test cases for the projects I'm working on. It will help me speed up the testing process and reduce manual effort. Second, I plan to use AI to analyze test results and automatically flag issues, improving the efficiency of our QA cycles. Lastly, I aim to leverage AI for generating realistic test data, which will help us test edge cases and improve the overall robustness of the application.

I’m excited about sharing these insights with my team and encouraging them to embrace AI in our daily testing work. Becoming an AI ambassador within the team feels like a natural next step, and I believe it will not only enhance our testing processes but also help in driving innovation in how we approach quality assurance. I plan to share my journey and learnings with my colleagues and even on platforms like LinkedIn to help others understand the value of AI in testing.

nice, ​@Yashvi_Mehta 

Cheers on completing the course and all the exercises!

Thank you for the time and effort you devoted to sharing your knowledge ​@parwalrahul .

Key learnings 

1. Before taking this course, I was exclusively using ChatGPT. However, after the first day, I realised how limited my tools were. There are numerous resources available that can help streamline tasks like generating test data, creating test cases, and coding more efficiently. FutureTools is an excellent platform for discovering these tools.

2. I learned that prompt engineering is essential for obtaining effective responses from an AI tool.

3. An important takeaway for me is the necessity of maintaining a tester's mindset while using AI tools. This means thinking critically, being skeptical, and not blindly accepting information.

(Thanks to all the other learners who have shared their experiences here!)

thinking critically, being skeptical, and not blindly accepting information.

​@Yastho nice. loved this point.

cheers on completing the course!

Coming with very limited knowledge on AI, this course was very helpful for me to understand AI evolution, tools and where and how can we use AI in testing.

Key learnings for me :

1. Getting insight on variety of AI tools available to leverage your day to day tasks.
2. Understanding on how AI will be helpful in automation testing and upskilling yourself in right direction , considering changing trends.
3. Prompt engineering - With right set of prompts one can get the accurate answers and even get the job done. something underrated but very important.
4. AI in QA activities like test documentation, test data generation and even helpful in guiding automation related tasks with detailing.
5. Future of testing like - Tricentris copilot is a unique example
   
   Thanks to Rahul and ShiftSync for adding a stepping stone!

​@parwalrahul 

Thank you for this course, as it gave lots of insights, ideas and encouraged me to use AI various stages in Software Test life cycle and I found a tag line  “QA-be_10x” productive.

Key Learnings from the Course

1. Understanding Generative AI in Testing

   • Gained insights into how generative AI can be applied specifically to software testing processes
   • Learned about the potential of AI to enhance test case generation, bug detection, and test automation

2. AI-Assisted Test Case Creation

   • Discovered techniques for using AI to generate more comprehensive and varied test scenarios
   • Understood how AI can help identify edge cases that human testers might overlook

3. Ethical Considerations and Limitations

   • Became aware of the ethical implications of using AI in testing, including data privacy concerns
   • Learned about the current limitations of AI in testing and the importance of human oversight

Team Discussion and AI Adoption

I shall recommend and share my learnings with my QA team to where in, I would like to :

• Share knowledge and insights gained from the course
• Brainstorm potential applications of AI in specific testing environment(Salesforce domain) in our case.
• Address any concerns or apprehensions team members may have about AI adoption
• Develop a strategy for gradually incorporating AI tools into our testing processes

Three Key Tasks for AI Adoption in the Next Three Months

1. Test Case Generation Enhancement

   • Implement an AI-powered tool to assist in generating more diverse and comprehensive test cases
   • Compare AI-generated test cases with manually created ones to assess effectiveness

2. Automated Bug Triage

   • Use AI to create bug reports, create a prompt to have detail bug reports.
   • Use AI to prioritize bugs based on severity and potential impact

3. AI-Assisted Test Script Generation

   • Utilize AI to generate Testing framework with likes of Selenium-Java-TestNG- with Cucumber framework or use to generate the same with Playwright
   • Implement AI recommendations to improve test script efficiency and coverage

Thank you once again for this amazing course Shiftsync and Rahul Parwal.

​@KajalS cheers on completing the course! Congratulations!

​@ameet213 nice.

cheers on completing the course! Congratulations!

Hi Rahul,

Thank you so much for the session, It helped me in various way and I can definitely say that I am using AI effectively for day to day QA tasks.

Here are my two bits-

Three Key Learnings from the Course:

1. Prompt Engineering and its Impact: A significant takeaway for me has been understanding the art of prompt engineering. Crafting precise and context-specific prompts greatly enhances the accuracy and relevance of AI outputs, making it an indispensable skill in leveraging AI tools effectively for testing.

2. Enhanced Test Strategy with AI: I've appreciated learning about the strategic enhancement that AI can bring to the test planning and execution phases. Integrating AI early not only streamlines the process but also ensures that testing strategies evolve alongside the applications they aim to improve.

3. Ethical Considerations in AI Testing: It's crucial to implement AI testing tools with an eye on ethics—ensuring transparency, fairness, and accountability. This ensures that the AI supports the testing team without introducing biases, upholding the integrity of our work.

Three Key Tasks Where I Plan to Use AI in the Next Three Months:

1. Automating Test Case Creation: I plan to use AI to transform requirements directly into detailed test cases. This automation will save time, increase consistency, and maintain high coverage across all testing scenarios.

2. Real-Time Analysis During Test Runs: Implementing AI for immediate analysis during test runs will pinpoint issues as they occur, allowing for faster adjustments and reducing the overall time spent on debugging.

3. AI-Enhanced Reporting for Strategic Decision Making: By utilizing AI to generate comprehensive reports, I aim to convert testing data into strategic insights that can guide future development projects and testing protocols.

Hello ​@parwalrahul  thanks for the course it was really insightful.

 

My key learnings:

• Grasping the Basics of Generative AI: Explored the workings of Generative AI models, the idea of domain-specific or task-specific large language models (LLMs), and the constraints associated with LLMs.
• Prompt Engineering: This technique provides a deeper understanding of search criteria, enabling more thorough and detailed analysis.
• AI as an Enhancer, Not a Replacement for Testers: Generative AI can take on repetitive or creatively demanding tasks, allowing testers to concentrate on strategic initiatives, exploratory testing, and advocating for quality.

 Key Tasks I Plan to Use Gen AI

• Root Cause Analysis: By using machine learning algorithms,  Gen AI can assist in analyzing the characteristics of defects and identifying their root causes more efficiently, which helps in prioritizing fixes and preventing similar issues in future releases.
• Dynamic Test Case Creation:  use Generative AI to analyze application requirements, user stories, and historical test data to automatically generate comprehensive test cases.
• Bug report

​@Nikhilkulkarni great job at completing the course.

all the best.

​@DamiS nice plans and good takeaways.

Congratulations on completing the course. all the best.

Three Key Learnings From The Course:

Understanding Generative AI Fundamentals: Courses emphasize foundational concepts like supervised learning, large language models, and generative adversarial networks. Learners grasp how generative AI creates realistic text, images, or videos, along with its limitations and ethical considerations.

Practical Applications in Work: Generative AI is showcased for transforming workflows across industries, enabling automation, and creating new opportunities. Learners explore real-world use cases, such as business task analysis, content generation, and responsible AI practices.

Experimentation and Responsible Usage: Courses encourage hands-on experimentation with AI tools in secure environments while highlighting governance frameworks to ensure ethical and responsible implementation of generative AI.

Three Key Tasks to Implement Gen AI in the Next Three Months:

Automated Test Case Generation: Generative AI can analyze software requirements, code, and user behavior to autonomously generate diverse and comprehensive test cases, including edge cases. This reduces manual effort and improves test coverage.

Dynamic Test Environment Configuration: Generative AI optimizes testing by dynamically configuring environments based on software requirements, ensuring efficient resource utilization and adaptability to changes.

Test Maintenance and Optimization: AI-driven tools can automate the maintenance of test cases, keeping them updated as software evolves, and prioritize critical tests to enhance defect detection efficiency.

Hello ​@parwalrahul,

Thanks for this activity. Over the past four weeks, I have learned so much that I didn’t feel like taking a course, as you made every session interactive and answered each individual's questions.

Loved ​​@Mustafa, ​@Daria, and ​@Kat hosting this, and also thanks for allowing participants to express themselves and ask questions.

My takeaways from this course:

1. AI is powerful, and so are we.

With the evolution of ChatGPT, the way people work has changed. It has made us push our limits. There have been so many advancements—tools and breakthroughs in manufacturing, IT, health industries, etc. You have made us know AI and how we can embrace it by showing us different powerful AI tools. My fav is Napkin, as always.

2. AI is always a double-edged sword.

We are seeing so many progressions, yet we need to know where we need to use them and where we shouldn’t. It can even make us less creative. Use it like an API to the brain. As in, even if you ask how to create a nuclear reactor, it helps, but you need to know what you’re going to do, mindfully. And we need to remember one thing: we are providing instructions to it, and it shouldn’t be the other way around—which is happening, though. So we need to be mindful.

3. Leverage AI in your work and be more productive.

In these 4 sessions, you have showcased details on where AI has started, the difference between AI and GenAI, RAG, how we can leverage AI, showcase etc.., Take your daily activities, check the feasibility of involving AI, assess the quality, and provide the numbers. It matters. It’s ok to fail while doing this, and in this process, you’ll learn more, and it even demands a new you.

Tasks:

• Take some time every everyday, every week and check the new things happening.  As AI keeps evolving, so do we.
• Use the ways we have explored in the session to reduce information obesity.
• Don’t limit yourself to only a tester; try to assess the logs and develop some scripts that you thought were not the work of a tester.

Thanks for all the learnings, Team.

Thank you Rahul, Mustafa. Below is my few key learning and task. Thanks for creating such a wonderful session.

 Key Takeaways from the Course:

1. Gen AI as a Testing Copilot
   It can assist with test case generation, code reviews, and even support exploratory testing by suggesting edge cases.

2. Prompt Engineering Matters
   The output quality depends heavily on how we communicate with Gen AI tools. Clear, context-rich prompts lead to better, more accurate results.

3. AI in Testing is a Mindset Shift
   It’s not just about the tools—it’s about rethinking how we approach testing, streamline workflows, and focus on higher-value tasks.

4. AI-Driven Bug Prediction and Detection
   Learned how machine learning models can predict potential defects by analyzing historical defect data and real-time logs.

5. Enhancing Performance Testing with AI Insights
   Use AI to identify system performance trends, uncover bottlenecks, and even predict failures before they impact users.

Where I Plan to Use Gen AI in the Next 3 Months:

1. Automated Test Data Generation
   To speed up testing cycles and improve coverage through diverse and scalable data sets.

2. Drafting User Stories & Acceptance Criteria
   Supporting better alignment with product teams and improving clarity in requirements.

3. Creating Lightweight Documentation
   Summarizing QA notes and test results using AI to save time and improve communication.

4. Defect Pattern Analysis
   To proactively identify recurring issues and optimize preventive test coverage.

​@Mustafa I am yet to receive my certificate.