Ai4Software Conference
This session is a practical overview of implementing private LLMs. You'll get a fundamental understanding of LLMs and how private versions differ from public models. We'll also explain why LLMs shouldn't be the only ingredient in your AI strategy, and other factors that play a role in LLM integration and the overall success of AI strategy.
We'll discuss infrastructure needs and customization, basic architecture considerations, and how to approach integration of these systems within existing IT environments. We'll give some realistic scenarios and use cases.
Data privacy, security, and regulatory compliance concerns
Scalability of AI solutions
Managing costs
Identifying opportunities for efficiency
Pitfalls, challenges, caveats, and KBYG
Chris is an experienced leader in enterprise technology with over two decades in training, coaching, and emergent technology enablement, particularly in project management. He excels in creating transformative technology training programs focused on software development, data environments, and agile methodologies. His expertise encompasses enterprise software engineering, advanced analytics, data engineering, and the application of AI and machine learning in business. Chris combines design thinking and lean technology management to innovate in product development and operational strategies, impacting various sectors such as government, education, and multinational corporations.
Here are some ways AI can be integrated into DevSecOps:
Code Analysis and Review: AI-powered tools
Automated Testing: AI algorithms can facilitate automated testing by generating test cases, predicting potential failure points, and optimizing test suites. This accelerates the testing process and improves test coverage, leading to more robust and secure applications.
Anomaly Detection
Predictive Maintenance
Security Automation
Threat Intelligence
Behavioral Analysis
Continuous Monitoring and Remediation: AI-powered monitoring
Compliance Management
By Integrating AI Into DevSecOps Practices, Organizations Can Achieve Faster Time-To-Market, Improved Security Posture, And Greater Operational Efficiency, Ultimately Enhancing The Overall Quality And Reliability Of Software Products.
Naser is a thought leader adept at driving enterprise-wide digital transformations, notably transitioning organizations from project-centric to product operating model. With a focus on product management, enterprise-scale agile adoption, accelerated DevOps implementation, AI integration, and cloud migration, he has led several key initiatives benefiting over 12 million patients, providers, customer service, and prospects experiences. These efforts prioritize consumer-centricity, continuous discovery, continuous delivery, and alignment with organizational objectives, driving revenue growth, efficiency, and automation.
In this session, we will explore the groundbreaking capabilities of GPT-Engineer, an open-source project that utilizes generative AI to create full-fledged code for software applications. We will just use the PM specification, or to be more precise, simple natural language prompts, and you will see the whole web application code is generated in seconds. This hands-on talk will guide you through the process of setting up GPT-Engineer and integrating it into your development workflow. We will discuss in detail the features of advanced code generation systems.
Additionally, we will introduce an advanced generative AI-powered agent to test the application quickly and improve it to great quality and efficiency. We will demonstrate how simple it is to ensure that the generated code meets high-quality standards using the power of AI. By combining GPT-Engineer and AI in software testing, you will learn how to create and validate application code quickly with almost zero test maintenance.
As a developer, you can learn how GPT-Engineer helps you reduce time and effort, achieve a streamlined workflow, customize, and perform rapid software prototyping. All these benefits accelerate the development cycle and enable faster feature delivery. If you are a software testing professional, you can learn to test complex test scenarios using plain English (or any other natural language) prompts, intelligent AI-based testing capabilities, efficiency in QA through generative AI, GPT-Engineer’s role in CI/CD, and how to use AI to have zero test maintenance. Quite evidently, all of these capabilities lead to improved application accuracy with minimum effort.
Join Artem Golubev from testRigor to discover how the synergy between GPT-Engineer and smart QA can revolutionize software development. Learn how to employ the power of generative AI for efficient code creation and robust testing, enabling your team to innovate faster and deliver high-quality applications quickly with ease.
Artem Golubev is a co-founder of testRigor, a YC company. He is excited about helping companies to become an order of magnitude more effective in QA and deliver software faster. Artem started his career 25 years ago by building software for logistics companies. Since then, he worked at companies like Microsoft and Salesforce, where he learned about best practices and top technologies in QA. He is now bringing those technologies to other companies to allow them to catch up with the software giants and become more efficient in testing. testRigor AI empowers companies like Netflix, Cisco, Burger King, and many more to build test automation faster and spend less time on test maintenance.
In line with the conference theme of AI advancements in software engineering, my presentation will delve into Retrieval-Augmented Generation (RAG). RAG addresses the knowledge cutoff issue in LLMs like ChatGPT by integrating external data sources dynamically at inference time. This empowers LLMs to access up-to-date information, enhancing accuracy and relevance while mitigating AI hallucination risks. Through examples, I'll showcase RAG's efficacy across software engineering domains, fostering innovation and efficiency.
Participants will gain a deep understanding of Retrieval-Augmented Generation (RAG) and its role in overcoming the knowledge cutoff issue in Large Language Models (LLMs) within software engineering. They'll explore how RAG updates LLMs' understanding of the world, enhances performance during inference, and the mechanisms behind it. Attendees will grasp the significance of retrievers in selecting relevant passages and learn about RAG's dual nature, including its benefits in mitigating model hallucination and limitations such as impact on system responsiveness. Practical examples will provide insights into integrating RAG into software engineering practices for more efficient development processes.
Hagar Bendary Is A Highly Experienced Professional With A Bachelor's Degree In Computer Science , Complemented By Two Diplomas In Software Development And Another From EPITA In AI And Machine Learning. She Have Excelled As A Kaggle Notebook Expert And Was Chosen By Kaggle For The Prestigious KaggleX Mentorship Program Sponsored By Google.
Her Career Journey Spans Diverse Roles, Including Positions In the Private Sector And Governmental Bodies, Such As The Ministry Of Economic Reform And The National Institute Of Governance And Sustainable Development. She Has Also Served As (AI) Track Supervisor At The ITI In Egypt.
Currently, Hagar Bendary Holds The Role Of Solution Architect At Etisalat E& In The UAE, Specializing In Data Analytics And Machine Learning.
Join Michael Arulfo, AI Principal Enterprise Architect at Boston Scientific, as he unveils the transformative power of AI Digital Architecture Strategy for your organization. In this enlightening keynote, Michael will share his unique perspective, honed from 25+ years of experience at the forefront of AI and digital healthcare. He'll guide you through the foundational principles and insights crucial for building a robust AI architecture, offering a framework to navigate the AI landscape with confidence. Whether you're just starting your GenAI journey or looking to elevate your existing AI strategy, this keynote will equip you with the knowledge and inspiration to scale your AI Strategy to the Enterprise.
Michael Arulfo, AI Principal Enterprise Architect at Boston Scientific. Michael leads GenAI and AI Architecture Strategy, shaping healthcare's digital future. His expertise is honed through roles at the Mayo Clinic, Allina Health, Optum.AI and UnitedHealthcare, driving AI platform development and scaled AI architecture design for the Enterprise. Michael is a founding member of the Chief Architect Forum and Chairman of BETA.MN (Minnesota’s oldest and largest tech startup accelerator and organizer of Twin Cities Startup Week). A leader in technology innovation, Michael champions AI and GenAI’s transformative potential in healthcare, fostering business agility and improving healthcare outcomes for patients
With over 20 years in project management, I've spearheaded the integration of AI technologies across diverse sectors, enhancing scope management, risk mitigation, and stakeholder engagement. My expertise spans deploying AI for predictive analytics, automating workflows, and optimizing resource allocation. I've led teams in adopting Agile methodologies, enriched by AI for dynamic project adaptation. My work in AI-driven project monitoring has set new benchmarks for success, leveraging data analytics for proactive decision-making. A recognized thought leader, I've contributed to the evolution of project management practices, demonstrating AI's transformative potential in achieving unparalleled efficiency and strategic depth.
AI transforms Agile software development, boosting speed and quality for managers, product owners, and Scrum teams. 80% of project managers foresee significant role changes due to AI, potentially elevating productivity by 40%. However,
AI empowers SDLC phases:
Initiation: Guides investment and risk decisions.
Planning: Generates user stories and estimates.
Execution: Tools like Co-Pilot streamline coding.
Rollout: Monitors KPIs and provides insights.
Closure: Simplifies task completion and knowledge management.
By fostering team motivation, efficiency, and data-driven decisions, AI ensures higher success rates and greater value for stakeholders.
AI revolutionizes Agile project management, reshaping project manager roles. It promises up to 40% productivity surge but reveals a preparedness gap in AI adoption. Across phases:
Initiation: AI drives data-driven investment decisions.
Planning: Generates precise user stories and estimates.
Execution: Tools like Co-Pilot automate coding, boosting efficiency.
Rollout: Tracks KPIs efficiently, offering actionable insights.
Closure: Simplifies task completion and knowledge management.
AI fosters team motivation, efficiency, and data-driven decisions, ensuring higher success rates and stakeholder value.
Manoj Kumar Jain
Manoj Kumar Jain is a seasoned technology leader with over 25 years of industry experience, specializing in AI and data engineering. With extensive expertise in Agile principles and large-scale team management, he excels in fostering high-performing, self-organized teams. Manoj has led significant technical transformations, including serverless architecture and cloud migrations. Known for his integrity and empathy, he inspires teams with strategic insights and a strong focus on customer satisfaction. His thought leadership makes him a sought-after speaker, sharing valuable industry insights.
Vivek Patle
Vivek Patle is an accomplished project manager with 18+ years of experience, adept at leading diverse teams to successful outcomes. Proficient in problem-solving and decision-making, he ensures timely and budget-conscious project delivery. Passionate about AI and GenAI, Vivek optimizes workflows, boosts productivity, and drives success across domains. As a thought leader at the AI-software project management nexus, his deep expertise propels innovation and efficiency.
Have you ever wondered if AI was right for you? Is the timing is right, or should you wait a bit before jumping in? In this session, costa will share tips and tricks for getting started with implementing various forms of AI to aid in software Testing. He will also cover some of the top challenges with using aI in testing, and how to overcome those. Costa will finish with a Live Demo Of an AI Solution Used At A recent Client Project
-How To Get Started With AI In Testing
-Create a good AI test Strategy
-Do's And Don'ts With AI
-Leveraging GenAI For More Than Just Testing
-How to overcome the Top Challenges And Limitations
Costa is a recognized thought leader with over 30 years of experience in AI, mobile, & IoT. He has led transformations at iconic brands like Home Depot, Verizon, AT&T, Truist, Kodak, DirecTV, and Coca-Cola.
A visionary innovator, he had a breakthrough invention that was nominated for the top innovation award in Georgia. He founded Mobile Labs in the same year, providing a platform for device management in the Cloud. Costa has been a featured speaker at over 70 events to date.
Costa is a strategic advisor at EPAM, transforming organizations by creating winning test strategies. He is also active in the IT community with organizations such as QAI, TAG, and serves on the board of AQAA as its current President. He also hosts an annual hybrid conference in the fall, The Future of Testing.
This session embarks on a deep dive into the dual roles of AI in software testing, contrasting the complexities of testing AI systems themselves against the efficiencies gained by employing AI in testing processes. With AI technologies becoming both the creators and the subjects of testing, we find ourselves at a unique crossroads that challenges traditional testing paradigms. Through a combination of technical exploration, case study analysis, and forward-looking speculation, we will unravel the nuanced intricacies of testing AI-based systems—where unpredictability and non-deterministic behavior introduce unprecedented challenges—and how AI can be leveraged to enhance traditional testing methods. This comparative discussion aims to shed light on the evolving landscape of software testing, where the lines between tester and tested increasingly blur.
Brijesh Deb offers 25 years of expertise in software testing, AI leadership, and Agile transformations, adeptly guiding teams through the intricacies of technology and Agile methodologies. As a hands-on software tester, he maintains a strong connection to technology, enabling him to lead projects in high-tech sectors including Automotive, Avionics, Semiconductor, Space, Agriculture, and Energy. Brijesh excels in delivering customer-centric solutions, emphasizing AI's role in enhancing stakeholder and customer value. As an Agile Transformation Agent, he promotes cultural change by fostering collaboration and adopting Agile principles across organizational levels. Residing in the Netherlands, Brijesh is an active social media wordsmith, an avid student of anthropology, and enjoys quality time with his son
15+ years of experience in the Test Automation Domain, working in companies like JP Morgan Chase, BNP Paribas, Cornerstone OnDemand, and Infosys. For the past 3 years, working passionately on building an AI-powered Nocode Test Automation and Test Management platform where I work as a Product Evangelist.
Have below AI certification under my belt -
Given A Number Of AI-Related Talks
Given More Than 25+ Talks. Talk Videos Can Be Found Here - Http://Youtube.Peek.Link/2gox
The presentation will cover AI-driven API automation testing in Agile environments, focusing on enhancing testing efficiency and accuracy, achieving deeper test coverage, and ensuring dynamic adaptation to changing requirements. Key concepts include the integration of AI for automated test generation, the role of machine learning in predictive analysis and self-healing scripts, and strategies for overcoming adoption challenges. We'll explore real-world success stories, emerging trends in AI and API testing, and predictions for the future evolution of Agile testing strategies. The goal is to demonstrate how AI-driven testing can revolutionize Agile development, ensuring faster, more reliable software delivery.
Participants will learn how AI-driven API automation testing enhances Agile development, including methods for increasing test efficiency and accuracy. They'll understand the significance of AI in achieving extensive test coverage and adapting tests to evolving project needs. The session will provide insights into overcoming challenges in AI testing integration, selecting appropriate tools, and fostering a culture of continuous improvement. Attendees will explore real-world applications and future trends in AI-driven testing, gaining knowledge to implement these strategies in their projects. The objective is to equip participants with the skills to leverage AI for more effective, efficient, and adaptable testing processes within Agile frameworks.
With over a decade in software development and testing, I specialize in integrating AI-driven technologies into Agile workflows. My expertise spans developing AI algorithms for automated API testing, enhancing efficiency and accuracy across diverse projects. I've led teams in adopting AI for predictive analysis and dynamic test adaptation, significantly reducing time-to-market while maintaining high software quality. My work includes pioneering self-healing test scripts and leveraging machine learning for security testing, contributing to the evolution of Agile testing strategies. My passion lies in exploring emerging AI trends to keep Agile methodologies at the forefront of technological innovation.
AI Testing or Data Science testing vs. Software Engineering testing differences, different techniques, different metrics, difference Life Cycles.
The Data Science Life Cycle, Where QA and Testing fit into the Process of Model Development, what testing techniques to use, as well as what Metrics to collect that are different than the Software Development QA and Testing we are used to performing.
With over 24 years in software QA, Robert specializes in AI Testing, distinguishing it from traditional software testing. Collaborating with Fortune 100 companies, he navigates the complexities of AI Testing. In his talk, "AI Testing is NOT Software Testing," Robert illuminates the unique challenges and approaches in AI model testing. His expertise positions him as a leading voice in advocating for specialized testing methodologies in the AI era.
Struggling with test data bottlenecks? Discover how AI can transform your continuous testing process. Continuous testing is essential for maintaining high software quality in today's agile and DevOps environments. One of the significant challenges is generating and seeding test data to ensure comprehensive coverage and realistic testing scenarios. This session will explore how AI can automate and enhance this process, providing reliable, varied, and contextually relevant test data, along with data masking to protect sensitive information.
We will discuss the benefits of using AI to generate test data, including improved accuracy, reduced manual effort, and faster turnaround times. By leveraging AI, attendees will learn how to identify hardcoded data, generate additional data from predefined lists, convert text to test data functions, and enhance system resilience through chaos testing. Attendees will gain insights into integrating these AI-driven techniques within their continuous testing pipelines. Real-world examples and best practices will be shared to illustrate practical applications and benefits. Join us to see how AI can make your testing smarter and more efficient.
In today's fast-paced development environment, the ability to quickly and accurately generate test data is crucial for maintaining a robust continuous testing framework. This session will explore how AI can be harnessed to automate the generation and seeding of test data, ensuring comprehensive test coverage and improving overall software quality. We will also discuss data masking and its importance in protecting sensitive information during testing.
Attendees will learn about:
Join us to explore advanced methodologies that are enhancing test data management and enabling more efficient and effective continuous testing practices.
Abstract: Envision a testing realm infused with AI-driven superpowers, where a reliable AI companion revolutionizes the way, we approach testing. This companion doesn't just assist; it transforms the adventure of creating test cases that span the full spectrum of possibilities and pinpointing bugs in the most unexpected places. This is the essence of AI-augmented testing, a paradigm where AI elevates testers to maestros, orchestrating a symphony of enhanced augmented test intelligence. By turbocharging the testing process to be quicker, smarter, and more efficient, this approach doesn't merely impart insights but equips you with actionable strategies to bring these innovative concepts to life, making your work not only more productive but also genuinely enjoyable and engaging.
But this session goes beyond merely discussing the technological underpinnings (e.g., GNN, RAG, RGA, NLU). It's a rallying cry for test professionals everywhere to embrace an era where their skills are amplified to superhero proportions. Through a blend of real-world anecdotes and hands-on demonstrations, participants will gain firsthand experience in leveraging generative AI for crafting exhaustive manual test cases, automating intricate testing scenarios, and achieving bug detection with unprecedented accuracy. We'll delve deep into the art of prompt engineering and fine-tuning, demonstrating how to design precise prompts that guide Generative AI in executing highly specialized testing tasks, thus opening new horizons in test engineering prowess.
Get ready to be motivated, to absorb knowledge, and to witness the future of testing—a future where you're not merely adapting but thriving, propelled by the avant-garde wave of AI-Augmented Testing. This session is your gateway to joining an elite community at the forefront of the GAI revolution, setting new standards for what it means to be a tester in the digital age. Embark on this voyage to the cutting edge of testing and seize the opportunity to define the next era of test assurance!
Elevating Tester Roles with AI: Understand how AI-augmented testing transforms the role of testers from routine task executors to strategic problem solvers. Learn how testers can leverage AI to focus on more complex, creative, and strategic aspects of testing, thus elevating their role and value within development teams.
Mastering AI-Augmented Testing: Learn how to utilize AI-driven technologies to automate and enhance your testing processes. Gain hands-on experience with tools that enable you to generate comprehensive test cases and automate complex testing scenarios, significantly improving efficiency and coverage.
The Art of Prompt Engineering for Testing: Acquire skills in prompt engineering and fine-tuning, enabling you to craft effective prompts that guide generative AI in performing highly specialized testing tasks. Learn how to tailor these prompts to your specific testing needs, unlocking new dimensions of test engineering capabilities and enhancing your ability to test more creatively and thoroughly.
Jonathon Wright is a strategic thought leader and distinguished technology evangelist. He specializes in emerging technologies, innovation, and automation, and has more than 25 years of international commercial experience within global organizations. He is the Chief Technology Evangelist and heads up Product Engineering (R&D) for Eggplant a Keysight Technologies company. Jonathon combines his extensive practical experience and leadership with insights into real-world adoption of Cognitive Engineering (Enterprise and Generative AI). Thus, he is frequently in demand as a speaker at international conferences such as TEDx, Gartner, Oracle, AI Summit, ITWeb, EuroSTAR, STAREast, STARWest, UKSTAR, Guild Conferences, Swiss Testing Days, Unicom, DevOps Summit, TestExpo and Vivit Community. In his spare time he is the QA advisory lead for MIT for the COVID Paths Check foundation throughout the Coronavirus pandemic. He is also a member of Harvard Business Council, A.I. Alliance for the European Commission, chair of the review committee for the ISO-IEC 29119 part 8 “Model-Based Testing” and part 11 for the “Testing of A.I. based systems” for the British Computer Society (BCS SIGiST). Jonathon also hosts the QA lead (based in Canada) and the author of several award-winning books (2010 – 2022) the latest with Rex Black on ‘AI for Testing’.