President, Agile Developer, Inc.
Dr. Venkat Subramaniam is an award-winning author, founder of Agile Developer, Inc., an instructional professor at the University of Houston, and the creator of dev2next and Arc of AI conferences.
He has trained and mentored thousands of software developers in the US, Canada, Europe, and Asia, and is a regularly-invited speaker at several international conferences. Venkat helps his clients effectively apply and succeed with sustainable agile practices on their software projects.
Venkat is a (co)author of multiple technical books, including the 2007 Jolt Productivity award winning book Practices of an Agile Developer. You can find a list of his books at https://www.agiledeveloper.com. You can reach him by email at venkats@agiledeveloper.com or on twitter/X at @venkat_s.
AI Assisted Development: Accelerate Your Productivity
Venkat Subramaniam
Your typical day as a programmer involves many things among which significant time and effort goes into writing code, debugging, reasoning about code, writing tests, refactoring code, devising algorithms. Depending on the application and the environment, each one of these can be daunting in their own respect, not to mention the complexities that come with having to juggle between these for different areas of application. In this workshop, learn how to use AI based tools to assist you with your day-to-day development.
Learn to use AI to: -create implementations for both mundane and complex logic -create unit tests -reason about code -detect issues in code -write tests before and after code -refactor code -find solutions from problem descriptions -turn from imperative to functional style code -look for performance issues and improvements
Rather than hear lecture all day, come to his workshop to practice along. We will take several problems and code examples, discuss the details, use a few different AI tools, discuss the pros and cons of using them, learn from the exercises as to how to drive these tools to get the best results and improve our productivity.
AI Practice Lead, Callibrity
Mary is a Java Champion, and the AI Practice Lead at Callibrity, a consulting firm based in Ohio. She started as an engineer in Unix/C, then transitioned to Java around 2000 and has never looked back since then. After 20+ years of being a software engineer and technical architect, she discovered her true passion in developer and customer advocacy. Most recently she has serviced companies of various sizes such as IBM, US Cellular, Bank of America, Chicago Mercantile Exchange, in topic areas that included Java, GenAI, Streaming systems, Open source, Cloud and Distributed messaging systems. She is also a very active tech community leader outside of her day job. She is the President of the Chicago Java Users Group (CJUG), and the Chicago Chapter Co-Lead for AICamp.
Demystifying GenAI: Build a ChatGPT App with Vector Store
Mary Grygleski
With ChatGPT taking center stage since the beginning of 2023, developers who have not had a chance to work with any forms of Artificial Intelligence or Machine Learning systems may find themselves either intrigued by the “maze” of new terminologies, or some may be eager to learn more, while perhaps a smaller group may not actually want to get themselves into a territory that’s unknown to them.
We start by having a quick introduction to GenAI, ChatGPT, and all of those new terminologies around generative AI. Then we’ll dive right into the hands-on part, about how we can construct a ChatGPT-based app quickly, using state-of-the-art tools such as PgVector, which provides vector extension to the popular open source Postgres.
The lab will include the following concepts, with some having hands-on exercises: - LLM providers and APIs (for Java Developers: Spring AI, Langchain4j) - Integrating with ChatGPT models - Generating embeddings, working with Vector DB - Prompt engineering - Understanding RAG (Retrieval Augmented Generation) - Understanding Multi-Agentic Workflows - Building generative AI applications
President, Bosatsu Consulting, Inc.
Brian Sletten is a liberal arts-educated software engineer with a focus on forward-leaning technologies. His experience has spanned many industries including retail, banking, online games, defense, finance, hospitality and health care. He has a B.S. in Computer Science from the College of William and Mary and lives in Auburn, CA. He focuses on web architecture, resource-oriented computing, social networking, the Semantic Web, data science, 3D graphics, visualization, scalable systems, security consulting and other technologies of the late 20th and early 21st Centuries. He is also a rabid reader, devoted foodie and has excellent taste in music. If pressed, he might tell you about his International Pop Recording career.
Computers Aren't Brains and Bots Aren't People
Brian Sletten
We use metaphors, conversational styles, and other tricks to think about the process of synthetic learning and to help people feel more comfortable interacting with the software that we build and call AI. The reality of biological brains is so much more than our connectionist software, however, and our fixation on this point may prevent us from properly evaluating what we produce. Our choice of personality-oriented bots confuses laypeople and technologists alike about what is possible or even appropriate. At the intersection of metaphor, learning styles, user experience design, neuroscience, psychology, and biology is an interesting middle ground that can help ground us in what is possible and give us direction on how to proceed. This talk will walk you through these topics to help you navigate what you hear about and ultimately choose to do with AI systems. When we are confused about these boundaries, we may make bad and inappropriate choices about how to apply them.
President, Agile Developer, Inc.
Dr. Venkat Subramaniam is an award-winning author, founder of Agile Developer, Inc., an instructional professor at the University of Houston, and the creator of dev2next and Arc of AI conferences.
He has trained and mentored thousands of software developers in the US, Canada, Europe, and Asia, and is a regularly-invited speaker at several international conferences. Venkat helps his clients effectively apply and succeed with sustainable agile practices on their software projects.
Venkat is a (co)author of multiple technical books, including the 2007 Jolt Productivity award winning book Practices of an Agile Developer. You can find a list of his books at https://www.agiledeveloper.com. You can reach him by email at venkats@agiledeveloper.com or on twitter/X at @venkat_s.
It AI-n't What You Think!
Venkat Subramaniam
Innovations have transformed human lives, in ways that we can't imagine how people survived before. Yet, we do not embrace innovations readily and we shouldn't in most cases. Our time in this world is juxtaposed with yet another major innovation in our field. Is AI going to take over the world, our jobs, our way of life...and more are questions that are asked frequently these days. Come to this keynote to learn how to ride the new wave instead of being swept under.
⚙️ Navigating Software Quality - From Chaos to Control
Head of Technology, Thoughtworks India
An experienced technologist with a demonstrated history of working in the IT services industry, Vanya is a strategic consultant specialising in platforms, delivery infrastructure, evolutionary architecture and cloud native applications. In her current role as Head of Technology for Thoughtworks in India, Vanya shapes new pursuits, strategically advises on client projects, and formulates meaningful and resilient technology strategies. She is a passionate technologist with a knack for solving complex problems, at scale. She is also deeply involved in with open source communities.
Navigating Software Quality - From Chaos to Control
Vanya Seth
In today’s rapidly evolving software landscape, the line between chaos and control is often blurred. This talk explores the dynamic interplay of chaos and control in Software Quality Assurance, arguing that neither is inherently detrimental nor wholly beneficial. We will discuss how the controlled integration of emerging technologies such as generative AI into QA, coupled with the adaptive strategies of full stack testing, navigates this complexity.
Delve into emerging trends that balance these elements, fostering an environment where both chaos and control co-exist to drive excellence in software development.
⚙️ Panel - Building with AI: New Paradigms and Practical Strategies
President, UJUG
Software Engineer focused on CI/CD
Brian Sletten
President, Bosatsu Consulting, Inc.
Brian Sletten is a liberal arts-educated software engineer with a focus on forward-leaning technologies. His experience has spanned many industries including retail, banking, online games, defense, finance, hospitality and health care. He has a B.S. in Computer Science from the College of William and Mary and lives in Auburn, CA. He focuses on web architecture, resource-oriented computing, social networking, the Semantic Web, data science, 3D graphics, visualization, scalable systems, security consulting and other technologies of the late 20th and early 21st Centuries. He is also a rabid reader, devoted foodie and has excellent taste in music. If pressed, he might tell you about his International Pop Recording career.
Peter West
CEO, Qualiti
Peter’s experience includes founding Seva Development, where he helped companies ranging from startups to public companies including Microsoft to design and implement their QA and software engineering strategies. Prior to that he focused on building product and quality strategy at Silvervue (now Mingle Health). Currently a founder at Qualiti, a company focused on leveraging AI to take the work - but not the control - off of QA engineers, Peter's expertise in AI and software engineering have made him a prominent voice in the industry, including being named one of Utah’s AI 100 leaders for practical implementation of AI.
I have spoken at many local events, including meetups with over 100 people in attendance, panels with CTOs, CEOs, QA meetups, and Silicon Valley Bank panels.
Vanya Seth
Head of Technology, Thoughtworks India
An experienced technologist with a demonstrated history of working in the IT services industry, Vanya is a strategic consultant specialising in platforms, delivery infrastructure, evolutionary architecture and cloud native applications. In her current role as Head of Technology for Thoughtworks in India, Vanya shapes new pursuits, strategically advises on client projects, and formulates meaningful and resilient technology strategies. She is a passionate technologist with a knack for solving complex problems, at scale. She is also deeply involved in with open source communities.
Jacob Miller
Vice President of Data Science, Pattern
Jacob Miller is the Vice President of Data Science at Pattern, the largest ecommerce accelerator. Jacob's background and experience in academia, large corporations, and successful growth companies provide a unique perspective on what has proven successful and unsuccessful in AI and Data Science.
Panel - Building with AI: New Paradigms and Practical Strategies
Don Bogardus, Brian Sletten, Peter West, Vanya Seth, Jacob Miller
AI is redefining software development, opening new paths for solving complex problems and transforming workflows. This panel explores how developers can best leverage AI-driven tools in their daily work, from optimizing architectures to streamlining coding practices. Join industry experts for actionable insights, best practices, and a look at the skills needed to thrive in an AI-powered development landscape.
Founder, DefMacro Software, LLC
Raju Gandhi has been writing software for over two decades. Along the way he's been a software architect, consultant, author, teacher, and regularly invited speaker at conferences around the world. As both a software developer and a teacher, he believes in keeping things simple, preferring to understand and explain the “why” as opposed to the “how.”
Welcome to Arc of AI Conference
Raju Gandhi
Welcome and conference kickoff
Presentations: 59
Tracks
⚙️
AI in Development
How does AI influence your team's ability to quickly and safely create code? How can we be effective in letting AI generate code and what cautionary measures we need to put in place to make the best of that capability?
CEO, Miracle Finland Oy
Heli Helskyaho is the CEO for Miracle Finland Oy. Heli holds a Master’s degree (Computer Science) at the University of Helsinki and she is specialized on databases. At the moment she is working on her doctoral studies at the University of Helsinki. Heli has been working on IT since 1990. Heli is an Oracle ACE Director, and a frequent speaker in many conferences. She is the author of Oracle SQL Developer Data Modeler for Database Design Mastery (Oracle Press 2015) and a co-author of Real World SQL and PL/SQL: Advice from the Experts (Oracle Press 2016), Machine Learning for Oracle Database Professionals: Deploying Model-Driven Applications and Automation Pipelines (Apress 2021), and Extending Oracle Application Express with Oracle Cloud Features: A Guide to Enhancing APEX Web Applications with Cloud-Native and Machine Learning Technologies (Apress 2022). Heli is also a Data Vault 2.0 Certified Practitioner and holds several certificates on Oracle Technologies.
From RAGs to riches
Heli Helskyaho
Retrieval-Augmented Generation, RAG, is a technique to reduce hallucination of a large language model and to add your own data into the process without training a model. It is important that the RAG is reliable and is able to answer the user's questions as well as possible. Everybody knows what a naïve or basic RAG is but what are the more advanced versions of it and when should or should I not use them? In this session we will discuss how to add graphs to the RAG solutions (Graph-RAG) or how to use Agents (Agentic RAG) to improve the performance of a RAG.
Principal Engineer, Habuma
Craig Walls is a Principal Engineer, Java Champion, Alexa Champion, and the author of Spring AI in Action, Spring in Action, Spring Boot in Action, and Build Talking Apps. He's a zealous promoter of the Spring Framework, voice application development, and generative AI. When he's not slinging code, Craig is planning his next trip to Disney World or Disneyland and spending as much time as he can with his wife, two daughters, 1 bird and 3 dogs.
A Gentle Introduction to Generative AI
Craig Walls
It has become difficult to ignore the fact that Generative AI has become the most talked about technological advance in recent history. Chat applications such as ChatGPT and Bard have quickly put AI into the hands of the general public and almost every corporation is looking at ways to apply Generative AI to solve real business problems.
Hype aside, can Generative AI solve real problems? As a developer, you may be wondering how to implement Generative AI as a component in your projects. Can Large Language Models (LLMs) be used to answer real questions about my application's data?
In this example-driven session, we'll explore the essentials of Generative AI, including creating good prompts, providing context for prompts, binding completion responses to domain model objects, and enabling integration with custom data via functions and Retrieval Augmented Generation (RAG). Our exploration will touch on popular libraries for Python and Node, such as LangChain and LlamaIndex, but also touch on some of the newer options available to Java developers such as Spring AI and LangChain4J.
President, Agile Developer, Inc.
Dr. Venkat Subramaniam is an award-winning author, founder of Agile Developer, Inc., an instructional professor at the University of Houston, and the creator of dev2next and Arc of AI conferences.
He has trained and mentored thousands of software developers in the US, Canada, Europe, and Asia, and is a regularly-invited speaker at several international conferences. Venkat helps his clients effectively apply and succeed with sustainable agile practices on their software projects.
Venkat is a (co)author of multiple technical books, including the 2007 Jolt Productivity award winning book Practices of an Agile Developer. You can find a list of his books at https://www.agiledeveloper.com. You can reach him by email at venkats@agiledeveloper.com or on twitter/X at @venkat_s.
A Practical Introduction to LangChain4j
Venkat Subramaniam
Curious about AI and want to bring that into your Java applications? Let's move beyond hello world, let's take a look at some practical use cases of using AI and how we can build that into our applications using LangChain4j.
Developer Advocate, Qodo
Unlocking Innovation Through Expertise: David Parry, Developer Advocate
David Parry is an accomplished Director of Architecture with over 20 years of experience in Java development. It all began in 1996 when he discovered the fascinating world of programming, with a particular focus on Java applets. Throughout his illustrious career, David Parry has been involved in various noteworthy projects. He has successfully built and implemented content management systems for a wide range of clients, including the esteemed Johny Walker and its renowned keepwalking.com. Additionally, as a consultant at a Big 4 firm, David played a pivotal role in solving critical issues for numerous customers, demonstrating his expertise in handling complex and high-traffic web platforms. Never one to shy away from innovation, David Parry has expanded his skills to work on cutting-edge technologies such as mobile and embedded Android TV systems. Leveraging his expertise, he has delivered top-notch streaming services to customers, ensuring they have an exceptional viewing experience. Currently, David holds the position of Developer Advocate and Consultant overseeing strategic planning and execution of architectural designs for customers. With a deep understanding of software development principles and extensive experience in Java programming, he excels at providing valuable insights and guidance to his team. Having witnessed the evolution of Java development from its early days to its current state, David Parry's wealth of experience and strategic perspective, combined with his consulting work at a Big 4 firm, make him an invaluable asset in any project or organization he is a part of.
AI Assisted Coding: Navigating the Strengths, Challenges, and Future of Coding Assistants
David Parry
Artificial intelligence has revolutionized many aspects of software development, and AI-assisted coding tools are rapidly becoming indispensable in a developer's toolkit. This talk explores the current landscape of coding assistants, highlighting the tasks where they excel and the areas where they struggle. We’ll dive into practical strategies for mitigating the weaknesses of these tools, ensuring that developers can maximize their utility.
You'll gain an understanding of the array of AI coding assistants available today, their unique strengths, and how they fit into a developer's quiver. We’ll also look ahead to the future, offering predictions about upcoming improvements in AI-assisted coding and identifying the tasks likely to advance slower.
Finally, we will address a crucial question: How can developers build confidence that the output or advice from AI tools is reliable? Attendees will leave equipped with insights and actionable advice to effectively leverage AI in their coding workflows, enhancing productivity and quality in software delivery.
Chairman, NYJavaSIG
Frank Greco is a distinguished expert in Artificial Intelligence and Machine Learning, with extensive experience consulting for major corporations, including Google, AT&T, Lehman Brothers, NYSE, and Oracle, as well as numerous technology startups. His expertise spans AI/ML, cloud and mobile computing, technical education, and enterprise product management. Frank has a significant educational background, having founded the NY Java User Group (NYJavaSIG) and co-authored the international standard JSR381 Visual Recognition AI/ML API for Java. He is a prominent speaker at global technology conferences and is influential in shaping discussions about the intersection of AI/ML and business. As Chairman of the NYJavaSIG, Frank remains at the forefront of developer communities and continues to drive innovation and understanding in the ever-evolving world of technology. His work extends beyond business consultancy as he continues to shape the future of technology through leadership roles and impactful contributions to standards and practices in the field.
AI for Busy Java Developers
Frank Greco
Yep, we know you're knee-deep in production Java deployments and don’t exactly have time to learn about AI. But your manager is talking more about AI every day, and you’re reading unsettling posts about how GenAI will take your job. In this session, we’ll fast-track you through AI and Machine Learning—tailored just for Java developers who need to get the job done without the need to drill down into data science and complicated math. We’ll cover all the basics and explain how AI can be used in the software development process beyond simple code generation. You’ll walk away understanding where AI fits (and doesn’t fit), understand the ethical concerns, and how you can make yourself more productive and enhance your career direction.
Why AI Matters to Developers and Your Career Importance of Patterns Predictive AI (PredAI) vs Generative AI (GenAI) GenAI vs. Traditional Search Engines Prompt Techniques The Importance of Context for GenAI Retrieval-Augmented Generation (RAG) Systems Fine-tuning vs RAG Java Libraries for AI/ML AI and the Software Development Process Responsible AI and Ethics Demos!
⚙️ AI in the Browser - Testing Chrome's GenAI Integration
Senior Developer Evangelist, Hire Me!
Raymond Camden is a Senior Developer Evangelist looking for his next role. His work focuses on APIs ranging from document management to generative media creation with AI tools. He is the author of multiple books on development and has been actively blogging and presenting for over twenty years. Raymond can be reached at his blog (www.raymondcamden.com) or via email at raymondcamden@gmail.com.
AI in the Browser - Testing Chrome's GenAI Integration
Raymond Camden
Chrome is currently testing the ability for developers to use GenAI and LLMs directly within the browser itself. While still early on, and not as powerful as a direct access to an API service, this provides on-device GenAI features that can greatly enhance web applications. In this session, I'll discuss the current state of affairs and demonstrate how to make use of this today.
Dipankar Saha
Principal Solutions Ar...
Royal Bank of Canada US Wealth Management
Dipankar Saha
Principal Solutions Architect, Royal Bank of Canada US Wealth Management
I am a seasoned software professional having 20 years of work experience. For the past decade, I have been working in a technical leadership role in my current organization Royal Bank of Canada(RBC) US Wealth Management. I have been implementing impactful projects resolving customer challenges using cutting edge technologies. At present, I am producing solution architectures to innovate, solve business problems and foster growth in my organization. In my role I collaborate with various stakeholders within and outside of my organization including but not limited to business, vendors, executives, technical leads, developers and testing team. My contribution has earned several awards in my present and past companies. I have been a learner throughout my career, have accomplished several valuable certifications on latest technologies, architecture, cybersecurity products and have successfully applied them in my day to day job role. After working as a professional in software and finance for a long time, I am looking forward to utilize my expertise and experience to participate in activities outside of my regular job duties to give back to the community, learn new things and expand my network within tech industry.
AI in the database - talk to your data
Dipankar Saha
Business users rely heavily on business intelligence tools to create queries for analytics and dashboards. While the goal is to enable self-sufficiency, complexities in crafting SQL queries and a limited understanding of the underlying data warehouse often push users to seek help from development teams. These teams, already burdened with other tasks, face delays in delivering the required queries, slowing down the decision-making process.
This presentation introduces Snowflake Cortex, a powerful AI-driven tool that bridges this gap by enabling business users to access data from Snowflake using natural language queries. With Cortex, users can ask questions in plain English, eliminating the need for SQL expertise and reducing dependency on technical teams. By leveraging AI, organizations can streamline data access, empower business users, and accelerate insights without compromising on efficiency.
⚙️ Adding Generative AI to your Workflow with Google Gemini
Senior Developer Evangelist, Hire Me!
Raymond Camden is a Senior Developer Evangelist looking for his next role. His work focuses on APIs ranging from document management to generative media creation with AI tools. He is the author of multiple books on development and has been actively blogging and presenting for over twenty years. Raymond can be reached at his blog (www.raymondcamden.com) or via email at raymondcamden@gmail.com.
Adding Generative AI to your Workflow with Google Gemini
Raymond Camden
GenAI is a buzzword today, but if you move past the funny demos and scary/cool generated images, GenAI APIs have the possibility of adding powerful new features to your existing workflows. From summarization and categorization to image processing, these can be powerful tools when used carefully. Gemini is Google's latest AI model that is able to handle different types of information including text, code, audio, image and video. In this session, you'll learn how to get started working with Google Gemini, including how to use Google's AI Studio and integrating the APIs in JavaScript using Node.js.
Holistic Software Architect, Carducci Inc
Michael Carducci is a seasoned IT professional with over 25 years of experience, an author, and an internationally recognized speaker, blending expertise in software architecture with the artistry of magic and mentalism. His upcoming book, "Mastering Software Architecture," reflects his deep understanding of the multifaceted challenges of building resilient, effective software systems and high-performing teams. Michael's career spans roles from individual contributor to CTO, with a particular focus on strategic architecture and holistic transformation.
As a magician and mentalist, Michael has captivated audiences in dozens of countries, applying the same creativity and problem-solving skills that define his technology career. He excels in transforming complex technical concepts into engaging narratives, making him a sought-after speaker and emcee for tech events worldwide.
In his consulting work, Michael adopts a holistic approach to software architecture, ensuring alignment with business strategy and operational realities. He empowers teams, bridges tactical and strategic objectives, and guides organizations through transformative changes, always aiming to create sustainable, adaptable solutions.
Michael's unique blend of technical acumen and performative talent makes him an unparalleled force in both the tech and entertainment industries, driven by a passion for continuous learning and a commitment to excellence.
Architecture Patterns for AI-Powered Applications
Michael Carducci
Since ChatGPT rocketed the potential of generative AI into the collective consciousness there has been a race to add AI to everything. Every product owner has been salivating at the possibility of new AI-Powered features. Every marketing department is chomping at the bit to add a "powered by AI" sticker to the website. For the average layperson playing with ChatGPT's conversational interface, it seems easy however integrating these tools securely, reliably, and in a cost-effective manner requires much more than simply adding a chat interface. Moreover, getting consistent results from a chat interface is more than an art than a science. Ultimately, the chat interface is a nice gimmick to show off capabilities, but serious integration of these tools into most applications requires a more thoughtful approach.
This is not another "AI is Magic" cheerleading session, nor an overly critical analysis of the field. Instead, this session looks at a number of valid use-cases for the tools and introduces architecture patterns for implementing these use-cases. Throughout we will explore the trade-offs of the patterns as well as the application of AI in each scenario. We'll explore use-cases from simple, direct integrations to the more complex involving RAG and agentic systems.
Although this is an emerging field, the content is not theoretical. These are patterns that are being used in production both in Michael's practice as a hands-on software architect and beyond.
Architects must maintain their breadth, and this session will build on that to prepare you for the inevitable AI-powered project in your future.
⚙️ Beyond Chat and Code Completion: AI Agents for Software Development
Principal Consultant, globally
Internationally recognized speaker Kito D. Mann is the Principal Consultant at Virtua, Inc., specializing in enterprise application architecture, training, development, and mentoring with microservices, cloud, Web Components, Angular, and Jakarta/Java EE technologies; the co-host of The Stackd Podcast; author of JavaServer Faces in Action. Mann has participated in several Java Community Process expert groups (including CDI, JSF, and Portlets). Mann is also a Java Champion and Google Developer Expert in Web Technologies. He holds a BA in Computer Science from Johns Hopkins University.
Beyond Chat and Code Completion: AI Agents for Software Development
Kito Mann
LLMs have taken the world by storm. They can analyze, write, update, or refactor code, but they can't actually build software. AI agents, however, harness the power of LLMs to bridge this gap.
Given a detailed story, they can generate a step-by-step plan and execute each step. This may be as simple as making modifications to a set of project files or as complex as installing libraries, building and testing code—all accomplished autonomously with minimal human intervention.
Join us to explore the capabilities and limitations of AI agents for software development. We'll examine how they work, delve into their integration with developer workflows, and explore how they're reshaping the future of software creation.
Josh Long
Spring Developer Advocate
the Spring team
Josh Long
Spring Developer Advocate, the Spring team
Josh (@starbuxman) has been the first Spring Developer Advocate since 2010. Josh is a Java Champion, author of 7 books (including "Reactive Spring") and numerous best-selling video training (including "Building Microservices with Spring Boot Livelessons" with Spring Boot co-founder Phil Webb), and an open-source contributor (Spring Boot, Spring Integration, Axon, Spring Cloud, Activiti, Vaadin, etc), a Youtuber (Coffee + Software with Josh Long as well as my Spring Tips series ), and a podcaster ("A Bootiful Podcast").
Bootiful Spring AI
Josh Long
Artificial intelligence is here, but you don't have to be a data scientist and Python enjoyer to get somethign out of it! Remember, fort the vast majority of use cases, the name of the game is integration, and here the JVM ecosystem, and Spring in particular, are second to none! In this talk, we'll look at Spring AI, which brings the power and elegance of Spring Boot to AI engineering.
⚙️ Building Agentic APIs With LLM Tool Use & Knowledge Graphs
Developer Experience, Hypermode
William Lyon is an AI engineer at Hypermode where he works to improve the developer experience of building model-native apps. Previously he worked as a software developer at Neo4j and other startups. He is also the author of the book “Fullstack GraphQL Applications” and earned a masters degree in Computer Science from the University of Montana. You can find him online at lyonwj.com
Building Agentic APIs With LLM Tool Use & Knowledge Graphs
William Lyon
The true power of LLMs isn’t in building chatbots, but rather leveraging AI models for implementing agentic workflows in the applications we build, adding features to our apps powered by LLMs that interact with APIs and data sources directly. This talk will introduce the building blocks of adding LLM backed agentic features to your app and demonstrate how we can use them together to build model-native apps by chaining data and LLMs together, leveraging LLM function calling and tool use, and implementing knowledge graph RAG.
CEO, Miracle Finland Oy
Heli Helskyaho is the CEO for Miracle Finland Oy. Heli holds a Master’s degree (Computer Science) at the University of Helsinki and she is specialized on databases. At the moment she is working on her doctoral studies at the University of Helsinki. Heli has been working on IT since 1990. Heli is an Oracle ACE Director, and a frequent speaker in many conferences. She is the author of Oracle SQL Developer Data Modeler for Database Design Mastery (Oracle Press 2015) and a co-author of Real World SQL and PL/SQL: Advice from the Experts (Oracle Press 2016), Machine Learning for Oracle Database Professionals: Deploying Model-Driven Applications and Automation Pipelines (Apress 2021), and Extending Oracle Application Express with Oracle Cloud Features: A Guide to Enhancing APEX Web Applications with Cloud-Native and Machine Learning Technologies (Apress 2022). Heli is also a Data Vault 2.0 Certified Practitioner and holds several certificates on Oracle Technologies.
Chunking techniques for a RAG solution
Heli Helskyaho
A very important phase of a RAG (Retrieval-Augmented Generation) solution is chunking. Chunking defines how a text data will be split into smaller pieces of text called chunks. If you chunk wrongly, the vector search will not find the data, therefore using the right technique is important. What chunking techniques are available and how to minimize the risk of not finding the data using the right kind of technique? In this session we will explain the theory of chunking and show several examples of different chunking techniques and their results.
⚙️ Everything You Need to Know About Running LLMs Locally
Developer Advocate, Red Hat
Cedric Clyburn (@cedricclyburn), Senior Developer Advocate at Red Hat, is an enthusiastic software technologist with a background in Kubernetes, DevOps, and container tools. He has experience speaking and organizing conferences including DevNexus, WeAreDevelopers, The Linux Foundation, KCD NYC, and more. Cedric loves all things open-source, and works to make developer's lives easier! Based out of New York.
Everything You Need to Know About Running LLMs Locally
Cedric Clyburn
As large language models (LLMs) become more accessible, running them locally unlocks exciting opportunities for developers, engineers, and privacy-focused users. Why rely on costly cloud AI services that share your data when you could deploy your own models tailored to your needs? In this session, we’ll dive into the advantages of local LLM deployment, from selecting the right open source model to optimizing performance on consumer hardware and integrating with your unique data.
Let’s explore the journey to your own local stack for AI, and cover the important technical details such as model quantization, API integrations with IDE code assistants, and advanced methods like Retrieval-Augmented Generation (RAG) to connect your LLM to private data sources. Don’t miss out on the fun live demos that prove the bright future of open source AI is already here!
Slides: https://red.ht/local-llm
⚙️ Fast, Highly Available, In-Memory Vector Database for AI at the Edge
Arjav Desai
Consulting Member of T...
Oracle Americas Inc
Adao Oliveira Junior
Solutions Architect, Oracle
Adao Oliveira Junior is a cloud solutions architect who has worked in the technology industry for over two decades, five on cloud native solutions. Adao has experience in collecting high-level requirements and translating them into technical solutions, helping customers and partners around the globe. He also contributed to several open source projects and the Kubernetes community and holds Kubernetes certifications such as CKA, CKAD, and KCNA, among other cloud and industry certifications.
Arjav Desai
Consulting Member of Technical Staff, Oracle Americas Inc
I am a consulting software engineer in the Oracle's Helidon team, focusing on integration with various cloud providers/services and representing team in Microprofile's AI working group.
I have more than 20yrs of experience with a track record of designing cloud services and development frameworks; having been involved with OC4J, Weblogic, Glassfish, Oracle K8S Engine (OKE) and now Helidon. I am passionate about innovation, latest technologies and finding solutions to complex problems.
Outside of work, I like spend time with my family, volunteer in community and track/hike across state/national parks.
Fast, Highly Available, In-Memory Vector Database for AI at the Edge
Adao Oliveira Junior, Arjav Desai
Our new AI overlords have arrived, and developers have rushed to integrate cloud-based AI services into their applications. While their adoption in the cloud is facilitated by fast (usually secure) colocated access, their adoption at the edge is beginning to receive more attention. Explore the use of AI at the edge, including the infrastructure, scalability, integration and cost challenges faced. As a part of the solution, we introduce Oracle Coherence’s new vector features that enable us to deploy a lightweight, highly available, distributed in-memory vector database at the edge.
President, Agile Developer, Inc.
Dr. Venkat Subramaniam is an award-winning author, founder of Agile Developer, Inc., an instructional professor at the University of Houston, and the creator of dev2next and Arc of AI conferences.
He has trained and mentored thousands of software developers in the US, Canada, Europe, and Asia, and is a regularly-invited speaker at several international conferences. Venkat helps his clients effectively apply and succeed with sustainable agile practices on their software projects.
Venkat is a (co)author of multiple technical books, including the 2007 Jolt Productivity award winning book Practices of an Agile Developer. You can find a list of his books at https://www.agiledeveloper.com. You can reach him by email at venkats@agiledeveloper.com or on twitter/X at @venkat_s.
Functional Programming with the aid of AI
Venkat Subramaniam
Functional programming is a great alternative to imperative style of programming due to reduced complexity and ease of maintenance. However, most programmers have spent more time learning and practicing imperative style and often find it hard to program in the functional style. Hey, why not use AI to create functional style code? Great thought but we can't simply put AI on autopilot on this one. In this presentation, we will take an example driven approach to understand the power and perils of using AI to create functional style code.
Developer Advocate, Neo4j
Jennifer Reif is a Developer Advocate at Neo4j, speaker, and blogger with an MS in CMIS. An avid developer and problem-solver, she enjoys learning new technologies, sometimes on a daily basis! Her passion is finding ways to organize chaos and deliver software more effectively.
GraphRAG: Data with Context
Jennifer Reif
In this connected world, traditional data stores often make it difficult to find valuable relationships. By making them a key component of the model, contextualizing a set of data becomes incredibly simple. In this session, we will walk through what a graph database is and how it can transform your applications and data. Then, we will look at how graphs are lending their strengths to the AI industry through vectors and GraphRAG. Live demos will show developers how to interact with graph data and use it in technical systems. Join us to learn how graph databases are used to improve the data world and help developers easily extract/import connected data!
Code (slides link in readme): https://github.com/JMHReif/ai-pet-travel
⚙️ Harnessing Event-Driven and Multi-Agentic Architectures for Complex GenAI Workflows
AI Practice Lead, Callibrity
Mary is a Java Champion, and the AI Practice Lead at Callibrity, a consulting firm based in Ohio. She started as an engineer in Unix/C, then transitioned to Java around 2000 and has never looked back since then. After 20+ years of being a software engineer and technical architect, she discovered her true passion in developer and customer advocacy. Most recently she has serviced companies of various sizes such as IBM, US Cellular, Bank of America, Chicago Mercantile Exchange, in topic areas that included Java, GenAI, Streaming systems, Open source, Cloud and Distributed messaging systems. She is also a very active tech community leader outside of her day job. She is the President of the Chicago Java Users Group (CJUG), and the Chicago Chapter Co-Lead for AICamp.
Harnessing Event-Driven and Multi-Agentic Architectures for Complex GenAI Workflows
Mary Grygleski
Generative AI applications, in general, excel in zero-shot and one-shot types of specific tasks. However, we live in a complicated world and we are beginning to see that today’s generative AI systems are simply not well equipped to handle the increased complexity that is found especially in business workflows and transactions. Traditional architectures often fall short in handling the dynamic nature and real-time requirements of these systems. We will also need a way to coordinate multiple components to generate coherent and contextually relevant outputs. Event-driven architectures and multi-agent systems offer a promising solution by enabling real-time processing, decentralized decision-making, and enhanced adaptability.
This presentation proposes an in-depth exploration of how event-driven architectures and multi-agent systems can be leveraged to design and implement complex workflows in generative AI. By combining the real-time responsiveness of event-driven systems with the collaborative intelligence of multi-agent architectures, we can create highly adaptive, efficient, and scalable AI systems. This presentation will delve into the theoretical foundations, practical applications, and benefits of integrating these approaches in the context of generative AI. We will also take a look at an example on how to implement a simple multi-agent application using a library such as AutoGen, CrewAI, or LangGraph.
⚙️ How to build an email filter and classifier that runs locally using Java and Ollama
Freddy Guime
Distinguished Principa...
Expedia Group
Freddy Guime
Distinguished Principal Engineer, Expedia Group
Freddy is a Distinguished Principal Developer at Expedia. Always dealing with performance and usability he is always curious on how to make the overabundance of data useful for travelers, traders and consumers. Having worked with different technologies before has allowed him to come with solutions to rendering bottleneck problems. A Usability Guru, Freddy understands and bridges the concepts of high-throughput with usability within software.
He is also the author and maintainer of the javapubhouse.com, a podcast dedicated to tutorial topics in Java that covers everything from the use of the keyword volatile to the definition of beautiful code, also of javaoffheap.com, a java news podcast.
How to build an email filter and classifier that runs locally using Java and Ollama
Freddy Guime
My personal inbox is unruly, having more than 100,000 unread emails, and carrying over more than 5 years of emails it became increasingly harder to keep it under control. As such I was looking for solutions that could help me reign in that particular inbox, and even when I was willing to pay (a somewhat modest) sum for some plugin or service to move spam nothing really panned out. I decided then to instead create my own email spam filter / classifier.
Not wanting to "ship" the content of my inbox to a third party, (and because I'm cheap), I stitched together a local running solution using Java, Spring AI, and Ollama running Llama 3.2. On this session we will go over how to setup ollama, and llama3, and how to prompt it for email classification. We then use the mail api to move the different emails to its different folder for later review.
But wait, there's more! Because of the power of LLMs we can not just "only" ask it to find spam, but add rules to help me classify other emails (I have 'orders', 'newsletters', 'flyers'), showing how something tha used to be so complex becomes fairly simple! Today, the possibilities for using local LLMs are boundless!
So if you want to see how these locally run LLMs can be used, join in as we dive into taming the 100,000 email beast of my inbox!
President, Agile Developer, Inc.
Dr. Venkat Subramaniam is an award-winning author, founder of Agile Developer, Inc., an instructional professor at the University of Houston, and the creator of dev2next and Arc of AI conferences.
He has trained and mentored thousands of software developers in the US, Canada, Europe, and Asia, and is a regularly-invited speaker at several international conferences. Venkat helps his clients effectively apply and succeed with sustainable agile practices on their software projects.
Venkat is a (co)author of multiple technical books, including the 2007 Jolt Productivity award winning book Practices of an Agile Developer. You can find a list of his books at https://www.agiledeveloper.com. You can reach him by email at venkats@agiledeveloper.com or on twitter/X at @venkat_s.
Identifying and fixing Issues in Code using AI based tools
Venkat Subramaniam
Software vulnerability is a huge concern. What's lurking in code is a question that keeps passionate programmers up at night. Is there a memory leak, what about a race condition, oh what about security issues, are we violating purity of functions when we're not supposed to? We have to maintain code that others have written and it's not always easy and quick to detect those defects ticking away in the code. In this presentation we will use AI based tools to detect issues in code, using multiple examples, and apply automated fixes and will reason about our approach and the change.
AI Developer Advocate, JetBrains
After having a career as a Data Scientist and Developer Advocate, Cheuk dedicated her work to the open-source community. Currently, she is working as AI developer advocate for JetBrains. She has co-founded Humble Data, a beginner Python workshop that has been happening around the world. She has served the EuroPython Society board for two years and is now a fellow and director of the Python Software Foundation.
Is coding assistant as good as we thought in coding?
Cheuk Ting Ho
Nowadays coding assistants are everywhere, many IDEs are offering them as plugins, and are becoming more and more powerful. But it prompts us questions, is coding assistant as good as we want it to be? What can and can't these AI agents do? Will AI take my job?
In this talk, the speaker will explain the current state of AI coding assistants, what is in the market, and what they promise. The speaker will also, with some real experience from developers who have used coding assistants, explore the potential and limitations of the assistants. From there, we will also look into the future, predicting the landscape of the software engineering industry and as a developer how we can take advantage of the coding assistants instead of getting our jobs taken by them.
## Goal
To explain, in an as objective way as possible, the effect of AI coding assistants in a developer's career and to be proactive in preparing what's to come.
## Target Audience
Everyone who codes for a living or anyone who is enthusiastic about coding. The speaker expects all levels of familiarity with AI coding assistants.
Independent cloud application architect, Bolbeck llc
Juan started his career writing code to optimize truck routing in open pit mines about 20 years ago. Since then, he has delivered technical solutions for companies in multiple private and public sectors. His background includes IT consulting, development and delivery in companies like AWS, PWC and Booz & Co.. His current interests include, building smart applications, AI/ML, CI/CD, containers and WASM. He is also very interested in making tech teams productive and focused on building amazing applications instead worrying about automatable, mundane tasks. Finally, he firmly believes on the application of technologies for the improvement of the average person's lifestyle.
Navigating the New Frontier: Lessons from Building and Deploying Agentic AI Apps
Juan Peredo
Building GenAI Agentic based applications feels both familiar and unusual at the same time. While the core principles of software development—APIs, services, and infrastructure—remain, the introduction of agentic AI brings a new set of challenges like probabilistic models, semantic evaluation, and prompt security. These elements introduce a new layer of complexity that can be both exhilarating and perplexing.
In this session, we will discuss lessons learned from the journey in creating agentic AI applications. We will delve into:
- Understanding Agents: What are agents, and how can they be harnessed to create innovative user experiences? We will explore the different types of agents and their unique applications. - GenAI Pitfalls: Discover common pitfalls when striving for consistent results in GenAI applications. We will discuss strategies to mitigate these challenges and ensure reliable performance. - Debugging Probabilistic Models: Debugging probabilistic model-based solutions presents unique challenges. We will share practical techniques and tools to effectively troubleshoot and refine the use of models in apps. - Deployment Strategies: Learn how to deploy agentic AI applications efficiently. We will cover infrastructure considerations and security measures to ensure smooth and secure deployment.
Principal Engineer, Habuma
Craig Walls is a Principal Engineer, Java Champion, Alexa Champion, and the author of Spring AI in Action, Spring in Action, Spring Boot in Action, and Build Talking Apps. He's a zealous promoter of the Spring Framework, voice application development, and generative AI. When he's not slinging code, Craig is planning his next trip to Disney World or Disneyland and spending as much time as he can with his wife, two daughters, 1 bird and 3 dogs.
Penning Powerful Prompts: Crafting effective prompts to get the best from an LLM
Craig Walls
At it's core, Generative AI is about submitting a prompt to an LLM-backed API and getting some response back. But within that interaction there is a lot of nuance, particularly with regard to the prompt itself.
It's important to know how to write effective prompts, choosing the right wording and being clear about your expectations, to get the best responses from an LLM. This is often called "prompt engineering" and includes several patterns and techniques that have emerged in the Gen AI space.
In this session, we'll cover several useful prompt engineering techniques as well as some emerging patterns that are categorized within the "Agentic AI" space and see how to go beyond simple Q&A to turn your LLM of choice into a powerful ally in achieving your goals.
President, Kousen IT, Inc.
Author of "Mockito Made Clear", "Kotlin Cookbook", "Modern Java Recipes", "Making Java Groovy", and "Help Your Boss Help You". Conference speaker, developer, and publisher of "Tales from the jar side" newsletter and companion YouTube channel. Professor of Computer Science at Trinity College in Hartford, CT.
Prompt Stuffing vs RAG
Kenneth Kousen
As context windows on AI tools continue to grow, it becomes easier to add necessary information to the current request rather than go through the hassle of pre-processing your data and embedding it into a vector database. This talk will discuss both situations: when it is useful and appropriate to stuff the prompt, and when it is better to create embeddings and do a similarity search.
Code and slides: https://github.com/kousen/LangChain4JDemo (slides under src/main/resources)
Consulting Member of Technical Staff, Oracle Americas Inc
I am a consulting software engineer in the Oracle's Helidon team, focusing on integration with various cloud providers/services and representing team in Microprofile's AI working group.
I have more than 20yrs of experience with a track record of designing cloud services and development frameworks; having been involved with OC4J, Weblogic, Glassfish, Oracle K8S Engine (OKE) and now Helidon. I am passionate about innovation, latest technologies and finding solutions to complex problems.
Outside of work, I like spend time with my family, volunteer in community and track/hike across state/national parks.
Adao Oliveira Junior
Solutions Architect, Oracle
Adao Oliveira Junior is a cloud solutions architect who has worked in the technology industry for over two decades, five on cloud native solutions. Adao has experience in collecting high-level requirements and translating them into technical solutions, helping customers and partners around the globe. He also contributed to several open source projects and the Kubernetes community and holds Kubernetes certifications such as CKA, CKAD, and KCNA, among other cloud and industry certifications.
RAG with In-Memory Java Microservices
Arjav Desai, Adao Oliveira Junior
Learn why Retrieval Augmented Generation (RAG) has emerged as a critical need to augment Large Language Models (LLMs) w/ internal, non public data. Python is usually required for GenAI programming but we will show you a native In-Memory Java approach to RAG pipelines for LLMs. Explore GenAI in an open source, fully native Java ecosystem using Helidon Microservices framework and LangChain4j to supplement GenAI LLMs with your internal, corporate data using RAG to provide more precise and accurate responses, reduce hallucinations and increase transparency and trust. Join us as we dive into Java based RAG with LLMs and shape the future of Java and AI!
⚙️ RAG: Accuracy and Explainability in GenAI Applications
Developer Advocate, Neo4j
Jennifer Reif is a Developer Advocate at Neo4j, speaker, and blogger with an MS in CMIS. An avid developer and problem-solver, she enjoys learning new technologies, sometimes on a daily basis! Her passion is finding ways to organize chaos and deliver software more effectively.
RAG: Accuracy and Explainability in GenAI Applications
Jennifer Reif
Accuracy and explainability are critical in GenAI applications. When information from AI-integrated solutions is inaccurate, it can have severe and negative cascading repercussions. Having the best data at the right time is vital.
LLMs are not able to handle this on their own, but retrieval augmented generation (RAG) can help by providing curated data as context to an LLM, guiding it to an appropriate answer. This session will explore how vector and graph RAG address the shortcomings of LLMs, explaining their shared functionality as well as some ways they handle it differently. Finally, we will see how to build a GenAI application with RAG to see these concepts in action.
Code (slides link in readme): https://github.com/JMHReif/vector-graph-rag
Founder, Epistemic Data
Luke VanderHart is a developer, author and consultant with an emphasis on system design, data ontologies and functional programming. He has worked in a variety of domains for over 20 years including security, healthcare, intelligence, finance and energy. He has a B.A. in Philosophy and Linguistics, and views software technology as an exercise in applied philosophy and a tool to both learn about and create the world.
His current project is a startup that builds tools integrating LLMs and ontologies, to deeply ground them in verifiable fact and formal reasoning.
RDF and the future of LLMs
Luke VanderHart
RDF is an important data paradigm, and highly influential to the design of both Clojure and Datomic. We will explore its design, philosophy, and yes, its etymology. And we will learn how its conceptual framework makes it a uniquely effective tool for interacting with the new hotness: Large Language Models.
Can LLMs actually be useful, beyond the hype? Under what conditions can we use them in our data systems in an ethical and reliable manner? RDF can, perhaps, provide answers.
President, Agile Developer, Inc.
Dr. Venkat Subramaniam is an award-winning author, founder of Agile Developer, Inc., an instructional professor at the University of Houston, and the creator of dev2next and Arc of AI conferences.
He has trained and mentored thousands of software developers in the US, Canada, Europe, and Asia, and is a regularly-invited speaker at several international conferences. Venkat helps his clients effectively apply and succeed with sustainable agile practices on their software projects.
Venkat is a (co)author of multiple technical books, including the 2007 Jolt Productivity award winning book Practices of an Agile Developer. You can find a list of his books at https://www.agiledeveloper.com. You can reach him by email at venkats@agiledeveloper.com or on twitter/X at @venkat_s.
Refactoring to Modernize Java Applications
Venkat Subramaniam
IDEs have provided ways to refactor code for a long time now. In spite of their effectiveness, that journey is arduous and time consuming. Reluctance to refactor increases the cost of development. However, refactoring for the sake of doing so can lead to greater productivity loss as well. In this presentation we will use data driven approach. We will take examples of code, measure code quality, and then use automated code transformation tools to refactor the code, and then, once again, measure the quality of code and see how much we have improved. This can help us to not only refactor faster but also see the benefits realized and motivate us to move faster with greater efficiency.
Principal Engineer, Habuma
Craig Walls is a Principal Engineer, Java Champion, Alexa Champion, and the author of Spring AI in Action, Spring in Action, Spring Boot in Action, and Build Talking Apps. He's a zealous promoter of the Spring Framework, voice application development, and generative AI. When he's not slinging code, Craig is planning his next trip to Disney World or Disneyland and spending as much time as he can with his wife, two daughters, 1 bird and 3 dogs.
Spring AI in Action
Craig Walls
By now, you've no doubt noticed that Generative AI is making waves across many industries. In between all of the hype and doubt, there are several use cases for Generative AI in many software projects. Whether it be as simple as building a live chat to help your users or using AI to analyze data and provide recommendations, Generative AI is becoming a key piece of software architecture.
So how can you implement Generative AI in your projects? Let me introduce you to Spring AI.
For over two decades, the Spring Framework and its immense portfolio of projects has been making complex problems easy for Java developers. And now with the new Spring AI project, adding Generative AI to your Spring Boot projects couldn't be easier! Spring AI brings an AI client and templated prompting that handles all of the ceremony necessary to communicate with common AI APIs (such as OpenAI and Azure OpenAI). And with Spring Boot auto-configuration, you'll be able to get straight to the point of asking questions and getting answers your application needs.
In this session, we'll consider a handful of use cases for Generative AI and see how to implement them with Spring AI. We'll start simple, then build up to some more advanced uses of Spring AI that employ your application's own data when generating answers.
AI Developer Advocate, JetBrains
After having a career as a Data Scientist and Developer Advocate, Cheuk dedicated her work to the open-source community. Currently, she is working as AI developer advocate for JetBrains. She has co-founded Humble Data, a beginner Python workshop that has been happening around the world. She has served the EuroPython Society board for two years and is now a fellow and director of the Python Software Foundation.
Strategies to Solve LLM Hallucinations
Cheuk Ting Ho
Hallucinations have been a big pain in products that use LLM. Users expect high accuracy in answers and rely increasingly on LLM or AI assistants. Hallucinations would result from destroying the users' trust in real-life consequences. Solving it has been a high-priority task for AI researchers.
In this talk, the speaker will explain, in technical terms, what causes LLM to hallucinations. From there, the speaker will introduce a few strategies to minimize hallucination and show examples of designs and use cases.
## Goal
To educate the audience about LLM hallucination and to explore methods to minimize it.
President, Agile Developer, Inc.
Dr. Venkat Subramaniam is an award-winning author, founder of Agile Developer, Inc., an instructional professor at the University of Houston, and the creator of dev2next and Arc of AI conferences.
He has trained and mentored thousands of software developers in the US, Canada, Europe, and Asia, and is a regularly-invited speaker at several international conferences. Venkat helps his clients effectively apply and succeed with sustainable agile practices on their software projects.
Venkat is a (co)author of multiple technical books, including the 2007 Jolt Productivity award winning book Practices of an Agile Developer. You can find a list of his books at https://www.agiledeveloper.com. You can reach him by email at venkats@agiledeveloper.com or on twitter/X at @venkat_s.
TDD with the Aid of AI
Venkat Subramaniam
In spite of the many benefits, the industry wide adoption of TDD has been abysmal due to many impediments. With Generative AI tools, there's renewed interest in TDD. Creating tests with the aid of AI is a great idea but there are some caveats. In this presentation we will take a look at the benefits of using AI to create tests to drive the design of code and discuss the dos and don't to get the most our of this approach.
President, Bosatsu Consulting, Inc.
Brian Sletten is a liberal arts-educated software engineer with a focus on forward-leaning technologies. His experience has spanned many industries including retail, banking, online games, defense, finance, hospitality and health care. He has a B.S. in Computer Science from the College of William and Mary and lives in Auburn, CA. He focuses on web architecture, resource-oriented computing, social networking, the Semantic Web, data science, 3D graphics, visualization, scalable systems, security consulting and other technologies of the late 20th and early 21st Centuries. He is also a rabid reader, devoted foodie and has excellent taste in music. If pressed, he might tell you about his International Pop Recording career.
The Agent Protocol : Standard Communication Between Disparate Agents
Brian Sletten
Agentic AI is an exciting extension of the Large Language Model (LLM) and Retrieval Augmented Generation (RAG) models, but the capacity to make them interoperable is not going to happen on its own. The Agent Protocol is an emerging OpenAPI-compatible specification for describing an API to interact with Agents implemented by a variety of participants. It provides a standard model for interacting with existing platforms and agents that have been deployed to them.
This talk will introduce the protocol, describe the endpoints, discuss existing and emerging implementations, and talk about next steps in the field of interoperable agent systems.
⚙️ The Power and Perils of Using Copilot and ChatGPT for Application Development
President, Agile Developer, Inc.
Dr. Venkat Subramaniam is an award-winning author, founder of Agile Developer, Inc., an instructional professor at the University of Houston, and the creator of dev2next and Arc of AI conferences.
He has trained and mentored thousands of software developers in the US, Canada, Europe, and Asia, and is a regularly-invited speaker at several international conferences. Venkat helps his clients effectively apply and succeed with sustainable agile practices on their software projects.
Venkat is a (co)author of multiple technical books, including the 2007 Jolt Productivity award winning book Practices of an Agile Developer. You can find a list of his books at https://www.agiledeveloper.com. You can reach him by email at venkats@agiledeveloper.com or on twitter/X at @venkat_s.
The Power and Perils of Using Copilot and ChatGPT for Application Development
Venkat Subramaniam
Tools serve us well when we learn their power, know when to use them, and be wise in how to use them. AI tools are no different. In this presentation we will take a look at practical ways to make use of AI tools like Copilot and ChatGPT and how we can benefit from those and how to be effective in using them.
Head of Technology, Thoughtworks India
An experienced technologist with a demonstrated history of working in the IT services industry, Vanya is a strategic consultant specialising in platforms, delivery infrastructure, evolutionary architecture and cloud native applications. In her current role as Head of Technology for Thoughtworks in India, Vanya shapes new pursuits, strategically advises on client projects, and formulates meaningful and resilient technology strategies. She is a passionate technologist with a knack for solving complex problems, at scale. She is also deeply involved in with open source communities.
The power of AI in software supply chain
Vanya Seth
AI is revolutionizing the software supply chain, marking a pivotal moment in how software is developed, deployed, and maintained. From market research and ideation to coding and operations, AI's integration transforms every aspect of the software delivery value chain. This talk will delve into the superpowers of generative AI, its fundamental building blocks, and its impact on cross-functional roles in product teams.
Founder, Epistemic Data
Luke VanderHart is a developer, author and consultant with an emphasis on system design, data ontologies and functional programming. He has worked in a variety of domains for over 20 years including security, healthcare, intelligence, finance and energy. He has a B.A. in Philosophy and Linguistics, and views software technology as an exercise in applied philosophy and a tool to both learn about and create the world.
His current project is a startup that builds tools integrating LLMs and ontologies, to deeply ground them in verifiable fact and formal reasoning.
Thinking Outside the Chatbox
Luke VanderHart
Language models have a great deal of potential for helping us build powerful systems, but the epithet "AI" has in many ways done us a disservice. It has steered our collective imagination towards applications in which the LLM adopts a human or at least agent-like role.
But it isn't actually clear that this is the best way to use them. A language model is a powerful thing, and its ability to emulate a human is almost incidental. This talk will explore ways of thinking about LLMs first and foremost as models, instead of pseudo-people, and how this can unlock a new landscape of creativity about how to apply them.
CEO, Qualiti
Peter’s experience includes founding Seva Development, where he helped companies ranging from startups to public companies including Microsoft to design and implement their QA and software engineering strategies. Prior to that he focused on building product and quality strategy at Silvervue (now Mingle Health). Currently a founder at Qualiti, a company focused on leveraging AI to take the work - but not the control - off of QA engineers, Peter's expertise in AI and software engineering have made him a prominent voice in the industry, including being named one of Utah’s AI 100 leaders for practical implementation of AI.
I have spoken at many local events, including meetups with over 100 people in attendance, panels with CTOs, CEOs, QA meetups, and Silicon Valley Bank panels.
Transforming Software Testing and Quality with AI
Peter West
• Description: Dive into the cutting-edge applications of AI in software testing, from test case generation to autonomous execution. Gain insights into managing costs, selecting and optimizing models, and adapting to the fast-paced evolution of AI for ongoing projects. • Key Takeaways: • Harnessing AI for faster, more accurate quality feedback • Best practices for maintaining cost-efficiency and relevance • Real-world applications and lessons learned from industry leaders.
Slides from Presentation: https://docs.google.com/presentation/d/18plxg2CAtgx2MxoGvr9bC42Xo_NLKWBuKXNYBvcf7Ok/edit?usp=sharing
Lead Developer Advocate, Azul
Pratik Patel is a Java Champion and lead developer advocate at Azul Systems. He wrote the first book on 'enterprise Java' in 1996, "Java Database Programming with JDBC" and “Developing Open Cloud Native Microservices”. An all around software and hardware enthusiast with experience in the travel, healthcare, telecom, financial services, and startup sectors. Helps to organize the Atlanta Java User Group, frequent speaker at tech events, and master builder of nachos.
Understanding RAG Techniques and MCP
Pratik Patel
The AI application space is moving rapidly and there are new & better LLM models coming out frequently. You’ve seen articles and videos of using Retrieval Augmented Generation (RAG) that look amazing - but once you start trying to use basic RAG to build your own applications, you suddenly hit a wall and things don’t work as expected… which is very frustrating. In this session, we will take a step back, and understand the fundamentals of RAG. We’ll look at different RAG strategies and techniques. Understanding the fundamentals of LLMs is a good starting point, and then we’ll expand into the different approaches to RAG, and discuss how MCP (Model Context Protocol) can be used along with RAG. Here’s the topics we’ll cover:
LLMs are semantic search based tools Vectorization and how it relates to semantic search Choosing the right tokenization strategy Embeddings Contextual Retrieval RAG Hybrid Search Enhance RAG MCP basics Difference between MCP and RAG Examples of the RAG techniques, MCP Server integration, and a complete application to give you concrete takeaways to build your own AI application
⚙️ What is AI Native Development - and how can we prepare for the journey
Head of Developer Relations, Tessl
Simon Maple is the Founding Developer Advocate at Tessl and former VP of Developer Relations at Snyk, ZeroTurnaround, and IBM; a Java Champion since 2014, JavaOne Rockstar speaker, Duke's Choice award winner, Virtual JUG founder, and London Java Community co-leader.
What is AI Native Development - and how can we prepare for the journey
Simon Maple
Software development today is code centric, with code coupling what needs to be done and how to do it. AI enables a new path - spec-centric development, where users specify what they want, and AI handles the how. This new approach will make software dev faster, better and more inclusive - but getting there will be a journey. This session will describe what AI Native Development can be, why it's worth pursuing, and how we can leverage insights from our past Cloud Native and DevOps transformations to adopt effective AI native practices.
AI is making strides in the area of DevOps, assisting organizations with proactively monitoring and observing applications in production, and detect pattern of access, potential issues, and more. The presentations in this track will empower you in your journey to use AI in DevOps.
Principal Engineer, Habuma
Craig Walls is a Principal Engineer, Java Champion, Alexa Champion, and the author of Spring AI in Action, Spring in Action, Spring Boot in Action, and Build Talking Apps. He's a zealous promoter of the Spring Framework, voice application development, and generative AI. When he's not slinging code, Craig is planning his next trip to Disney World or Disneyland and spending as much time as he can with his wife, two daughters, 1 bird and 3 dogs.
Observing AI with Spring Boot and Spring AI
Craig Walls
Modern application observability involves tracking key metrics and tracing the flow of an application, even across service boundaries. Spring Boot 3 introduced some powerful metrics and tracing capabilities based on Micrometer to open a window into your application's inner-workings.
Among the things you might want to keep an eye on in your Generative AI applications are how many interactions and how much time is spent with vector stores and AI provider APIs and, of course, how many tokens are being spent by your application. And being able to trace the flow of prompts, data, and responses through your application can help identify problems and bottlenecks.
Great news! Spring AI comes equipped to record metrics and tracing information through Micrometer. In this session, you'll learn how to put Spring AI observability to work for you. You'll learn about the metrics it exposes as well as the keys you can use to build dashboards and tracing to build a window into your Generative AI applications.
Vice President of Data Science, Pattern
Jacob Miller is the Vice President of Data Science at Pattern, the largest ecommerce accelerator. Jacob's background and experience in academia, large corporations, and successful growth companies provide a unique perspective on what has proven successful and unsuccessful in AI and Data Science.
Principles of Applied AI for Organizations
Jacob Miller
Why do so few hyped AI pilots make it to production? How can projects fail faster or effectively scale into production? What organization structures, principles, and processes best enable success when building products with AI components? After many failures and successes building impactful products with AI components, Jacob walks through the frameworks and principles to maximize your AI product's chances of success. https://docs.google.com/presentation/d/1AEEmeMIlFJrSHy95sjW8-j3PI1qduHphRKKRzCqfevE/edit?usp=sharing
💁🏼
AI and Personalization
How can you use AI to craft responses that are personalized to your customers and users based on their various details that you can glean in from data and interaction patterns.
💁🏼 Empowering Accessibility: AI Challenges and Triumphs for People with Disabilities
Electronic accessibility expert and consultant, Consulting
I am a Web Accessibility Evangelist with over 35 years of experience in my field. I have been passionate about access technology my entire life. I believe that technology is an pathway to change for people with disabilities and feel that everyone should be able to take advantage of the opportunities technology provides. I am an early adopter that loves to test tools and help create the most accessible environments possible. I am knowledgeable in W3C 2.1, Section 508, user design, and user experiences. I have mastered a wide variety of assistive technologies, including Jaws for Windows, NVDA, VoiceOver for Mac, VoiceOver for iOS, Talkback for Android, and Dragon Naturally Speaking. I have assisted a large number of people with motor and physical impairments in the use of and acquisition of tools such augmentative communication and many alternative input devices.
Empowering Accessibility: AI Challenges and Triumphs for People with Disabilities
Lucy Greco
This talk will explore the intersection of (AI) and accessibility, focusing on the unique challenges and significant advancements when collaborating with people with disabilities. We will discuss the importance of including data from people with disabilities and the development of inclusive interfaces that cater to diverse needs.
slides: https://bit.ly/lucyiai This talk will give a brief overview of the Importance of accessibility in technology, and some of the Challenges in AI for People with Disabilities
Then we will talk over the reasons for some of the problems faced today and discuss ways to solve these problems. Once we have some understanding of the best ways to solve the underlying problems, we will then talk over some of the current Interface Design Challenges. And then close with a few innovative ideas on ways to make AI a better tool for all people.
💁🏼 Everyday AI: Practical Applications Beyond the Chatbot
Scott Davis
Director of Digital Ac...
Front Range Community College
Scott Davis
Director of Digital Accessibility, Front Range Community College
Scott Davis is a Web Architect and Digital Accessibility Advocate, focusing on the multisensory aspects of web development. In a world where half of all Google searches are done by voice, and 80% of all social media videos are watched with the sound off and closed captions on, accessibility is a springboard for innovation.
Everyday AI: Practical Applications Beyond the Chatbot
Scott Davis
In "Everyday AI: Practical Applications Beyond the Chatbot," we will explore how AI is omnipresent in our personal digital ecosystem, powering features like personalized recommendations, health tracking, voice recognition, and home automation. AI is making the smart devices in our lives -- phones, watches, speakers, cars, and homes -- smarter and more intuitive. This session will delve into how technologies like machine learning, natural language processing, and computer vision are transforming the way we interact with everyday objects, from controlling home environments to enhancing safety and convenience in vehicles.
We will also examine the practical challenges and ethical considerations of integrating AI into these devices, including data privacy, user consent, and accessibility.
💁🏼 Making LLM fine-tuning accessible with InstructLab
Developer Advocate, Red Hat
Cedric Clyburn (@cedricclyburn), Senior Developer Advocate at Red Hat, is an enthusiastic software technologist with a background in Kubernetes, DevOps, and container tools. He has experience speaking and organizing conferences including DevNexus, WeAreDevelopers, The Linux Foundation, KCD NYC, and more. Cedric loves all things open-source, and works to make developer's lives easier! Based out of New York.
Making LLM fine-tuning accessible with InstructLab
Cedric Clyburn
The rise of large language models (LLMs) has opened up exciting possibilities for developers looking to build intelligent applications. However, the process of adapting these models to specific use cases can be difficult, requiring deep expertise and substantial resources. In this talk, we'll introduce you to InstructLab, an open-source project that aims to make LLM tuning accessible to developers and engineers of all skill levels, on consumer-grade hardware.
We'll explore how InstructLab's innovative approach combines collaborative knowledge curation, efficient data generation, and instruction training to enable developers to refine foundation models for specific use cases. Through a live demonstration, you’ll learn how to enhance an LLM with new knowledge and capabilities for targeted applications, without needing data science expertise. Join us to explore how LLM tuning can be more accessible and democratized, empowering developers to build on the power of AI in their projects.
Slides: http://red.ht/instructlab-deck
💁🏼 Smarter AI: Combining LLMs and Rule Engines for Safer and Predictable Results
Architect and Engineer Leader, Independent
Alex Porcelli is a seasoned Architect and Engineer Leader with over 25 years of professional development experience. A passionate open-source advocate, he has actively contributed to projects like Drools, jBPM, Kogito, Hibernate, and more for over 15 years. Alex spent more than a decade at Red Hat, where he played key roles as an individual contributor and leader in the Business Automation product line. Most recently, at IBM, he led the establishment of BAMOE, IBM's first open-source Business Automation product. Alex is also a frequent international speaker at events such as IBM TechXChange, QCon, JavaOne, CodeOne, Red Hat Summit, and DevNation.
Smarter AI: Combining LLMs and Rule Engines for Safer and Predictable Results
Alex Porcelli
The rise of Large Language Models (LLMs) like ChatGPT has taken the world by storm, transforming science fiction into everyday reality. These models have shown remarkable potential for enhancing productivity and creativity, yet many enterprises are still trying to figure out how to integrate them effectively into their business operations. Enter a tried-and-true branch of Artificial Intelligence: decision engines, such as rule engines. These systems, rooted in Symbolic AI, provide the predictability and transparency enterprises require but are often overlooked in the current wave of AI hype. The key lies in combining LLMs' dynamic, adaptive capabilities with the structured, consistent decision-making power of rule engines. In this session, you'll learn how to combine the power of LLMs with the open-source Drools engine—one of the most widely used rule engines globally. Through practical examples, we'll explore how this approach enables businesses to unlock the potential of LLMs while maintaining safeguards with clear, explainable, and consistent decision-making.
Developer Advocate, Red Hat
Cedric Clyburn (@cedricclyburn), Senior Developer Advocate at Red Hat, is an enthusiastic software technologist with a background in Kubernetes, DevOps, and container tools. He has experience speaking and organizing conferences including DevNexus, WeAreDevelopers, The Linux Foundation, KCD NYC, and more. Cedric loves all things open-source, and works to make developer's lives easier! Based out of New York.
The Inner Development Loop, but for AI Models?—CANCELED
Cedric Clyburn
Think about the inner loop of development: building, running, and testing applications. This tried-and-true workflow has driven software innovation for years—so why not apply the same methodology to developing and iterating on AI models? Specifically, large language models (LLMs) that can understand and generate natural language to enhance your applications. In this engaging session, you’ll learn how developers and engineers can rapidly build and fine-tune customized LLMs, tailored with their own data to solve unique challenges.
We’ll explore InstructLab, an open-source project that simplifies the fine-tuning process by leveraging Parameter Efficient Fine Tuning (PEFT), making advanced AI development accessible even on consumer hardware. Through a hands-on live demo, you’ll see how model iteration can integrate into traditional developer workflows, to continually test and align a model to your application. This session will help you experience and practically understand the AI model lifecycle, and enable you to bring tailored LLMs into your development stack.
📖
AI and Ethics
Unleashing AI based algorithms have consequences. What's a better way that to learn from experts who will share their stories and experiences about the ethical impact of AI and provide guidance on how our use of AI can be responsible, legal, and ethical.
📖 AI and Ethics: Navigating the Future of Responsible Technology
Scott Davis
Director of Digital Ac...
Front Range Community College
Scott Davis
Director of Digital Accessibility, Front Range Community College
Scott Davis is a Web Architect and Digital Accessibility Advocate, focusing on the multisensory aspects of web development. In a world where half of all Google searches are done by voice, and 80% of all social media videos are watched with the sound off and closed captions on, accessibility is a springboard for innovation.
AI and Ethics: Navigating the Future of Responsible Technology
Scott Davis
In "AI and Ethics: Navigating the Future of Responsible Technology," we will explore the critical intersection of artificial intelligence and ethical decision-making in software development. As AI technologies become increasingly integrated into every aspect of society, from healthcare to finance to simply driving your car, it is essential to address the ethical implications surrounding their use. This session will cover key topics such as bias in AI models, algorithmic transparency, and corporate attitudes towards data privacy.
If you buy a smart lightbulb, does the vendor also have the right to know each time you turn it on? By the end of the session, participants will have a clearer understanding of the ethical responsibilities developers face when integrating AI into their systems.
Founder, Epistemic Data
Luke VanderHart is a developer, author and consultant with an emphasis on system design, data ontologies and functional programming. He has worked in a variety of domains for over 20 years including security, healthcare, intelligence, finance and energy. He has a B.A. in Philosophy and Linguistics, and views software technology as an exercise in applied philosophy and a tool to both learn about and create the world.
His current project is a startup that builds tools integrating LLMs and ontologies, to deeply ground them in verifiable fact and formal reasoning.
AI as a Humanism
Luke VanderHart
Building software systems that can affect the world is not a value-neutral activity, and this is especially true for systems using very new, potentially very powerful tools such as large generative models. It is essential that builders of such systems are aware of the potential issues at play, and how they intersect with humanity.
This talk outlines some of the key issues around AI deployment and adoption and how they play out in society. It will add context to many of the hyperbolic claims emerging from the public discourse, and provide a conceptual toolbox for articulating which use cases of AI are likely to improve the human condition and which are likely to make it worse.
Scott Davis
Director of Digital Ac...
Front Range Community College
Scott Davis
Director of Digital Accessibility, Front Range Community College
Scott Davis is a Web Architect and Digital Accessibility Advocate, focusing on the multisensory aspects of web development. In a world where half of all Google searches are done by voice, and 80% of all social media videos are watched with the sound off and closed captions on, accessibility is a springboard for innovation.
Bridging the Digital Divide: Empowering Accessibility Through AI Innovations
Scott Davis
"Bridging the Digital Divide: Empowering Accessibility Through AI Innovations" explores how artificial intelligence (AI) is playing a pivotal role in making digital spaces more inclusive. This talk will showcase the transformative potential of AI technologies such as natural language processing, computer vision, and machine learning, highlighting their ability to enhance accessibility. From AI-powered screen readers and voice-controlled interfaces to real-time translation and personalized learning tools, this session will delve into practical examples and case studies where AI has provided individualized solutions that meet diverse needs.
Founder, tsrct inc
Building on interesting ideas for 25 years in tech, from mobile, to security, to platforms, and now universal trust.
Enhancing AI Systems with Provenance and Trust
Saurabh Gupta
This presentation explores how the open-standards based tsrct platform enhances AI systems by ensuring data authenticity, model transparency, and system accountability through advanced provenance tracking and cryptographic verification. Attendees will learn how tsrct supports reliable AI by grounding algorithms in trustworthy data, enabling real-time verification for agentic workflows, and combating misinformation and deep fakes. Additionally, tsrct’s open document standard will be discussed, showing how it facilitates auditable and secure data interchange. This session will show actionable strategies for AI developers and architects focused on building ethical, robust, connected, and helpful AI systems.
📖 Interpreting Data: Wielding Data for Good and Evil in the AI Era
Developer Advocate, Neo4j
Jennifer Reif is a Developer Advocate at Neo4j, speaker, and blogger with an MS in CMIS. An avid developer and problem-solver, she enjoys learning new technologies, sometimes on a daily basis! Her passion is finding ways to organize chaos and deliver software more effectively.
Interpreting Data: Wielding Data for Good and Evil in the AI Era
Jennifer Reif
Data is a powerful tool that permeates our everyday lives. As both users of data systems and market consumers, we know how data can be a superpower for good and evil. Increasing technology capabilities bring more opportunities for benefit and destruction, further expanding in today's AI era. How can we balance these seemingly competing interests? And are the benefits worth the cost?
In this session, we will explore ways data can be used to make the world a better place or be used against us. We will discuss technologies and tools that help us as developers wield it for good and recognize and combat misuse. Learn how to use data to make a positive impact on the world and set up safe practices for the future.
Software Developer, AJUG/Devnexus
Glenn Renfro is a core committer for Spring Cloud Task, Spring Batch, and Spring Cloud Data Flow and a Java Champion. He has 15 years of experience in designing, building, and delivering enterprise-level applications in Java and 21 years total of software development experience.
Nathaniel Schutta
Architect, Thoughtworks
Nathaniel T. Schutta is a software architect and Java Champion focused on cloud computing, developer happiness and building usable applications. A proponent of polyglot programming, Nate has written multiple books, appeared in countless videos and many podcasts. He’s also a seasoned speaker who regularly presents at worldwide conferences, No Fluff Just Stuff symposia, meetups, universities, and user groups. In addition to his day job, Nate is an adjunct professor at the University of Minnesota, where he teaches students to embrace (and evaluate) technical change. Driven to rid the world of bad presentations, he coauthored the book Presentation Patterns with Neal Ford and Matthew McCullough, and he also published Thinking Architecturally and Responsible Microservices available from O’Reilly. His latest book, Fundamentals of Software Engineering, is currently available in early release.
Trust but Verify - The Ethics of Non Deterministic Systems
Glenn Renfro, Nathaniel Schutta
“Move fast and break things” may make for a good bumper sticker but in the real world, things are far more nuanced. The integration of Artificial Intelligence (AI) services into your architecture raises ethical concerns, especially when these systems are inherently non deterministic. How do you trust the results when you can’t reason about how they were achieved? More importantly, what are the appropriate uses of these technologies? This talk examines some of the considerations you need to make when adding AI services to your architecture. We will explore the ethics of trust as well as how we can engineer solutions with appropriate guardrails and why people remain a critical part of the process. Trust isn’t binary, this talk will help you navigate the continuum of good enough.
You can find the PDF for our slides here: https://github.com/cppwfs/canihaveyourorder/blob/main/Trust%2520but%2520Verify%25202a.pdf
🏦
AI at Work
How is AI being used out in the wild. Learn from passionate developers who like to share their journey and experience and show case how AI has played significant role at their work.
🏦 AI Adoption Adventures: Our Playbook for Driving User Engagement!
Erica Woods
Director, Consultant P...
Apex Systems
Erica Woods
Director, Consultant Programs and Philanthropy, Apex Systems
Erica Woods is the Director of Contractor Programs and Philanthropy at Apex Systems. Her focus is on overseeing programs, teams, communication channels, and other resources that support their IT Consultant Community of 16,000+. Erica also oversees corporate philanthropy efforts and acts as a technical community evangelist for various STEM programs/nonprofits. She has 18 years of experience in the IT staffing and solutions world and an MBA from Loyola University. She is a Professional and Career Development Author for the MSSQLTips.com online technical community, presents Career Development sessions for various communities, including SQL Saturdays, Code Camps, PMI chapters, IIBA chapters, BA World conferences, and provides internal and external Leadership and Hiring Coaching. Erica is a Co-Founder of the ‘Baltimore Techies for Good’ Meetup group, and Co-Founder/Co-Organizer of the Tampa Tech4Good Meetup group, which are monthly events that bring together technical and marketing folks looking for skills-based volunteering opportunities with nonprofits in need of technology help/guidance. She is also one of the three Founders of the ‘100 Techies Who Care’ group in Tampa, which launched in 2023.
AI Adoption Adventures: Our Playbook for Driving User Engagement!
Erica Woods
In an era where AI tools are reshaping the workplace, effective adoption strategies are crucial for both uncovering potential application and driving tool utilization to influence creativity, save time and drive ROI. This session will shine a light on the specific techniques we used to drive company-wide user engagement and utilization of Microsoft Copilot, our internal AI tool of choice.
We will dive into 8+ key strategies that we found impactful in fostering a culture of adoption within our organization. We will discuss ideas such as: identifying Change Champions, conducting training sessions, and leveraging on-demand resources to empower users. Attendees will learn how to create a vibrant community around AI, share success stories, and utilize analytics to track progress and drive continuous improvement.
Participants will leave equipped with actionable ideas to help transform team members into enthusiastic advocates for AI tools. Whether you're a leader looking to enhance your team's capabilities or a practitioner eager to implement change management best practices, this session will provide stops for your respective roadmaps to drive awareness, education and change!
President, Bosatsu Consulting, Inc.
Brian Sletten is a liberal arts-educated software engineer with a focus on forward-leaning technologies. His experience has spanned many industries including retail, banking, online games, defense, finance, hospitality and health care. He has a B.S. in Computer Science from the College of William and Mary and lives in Auburn, CA. He focuses on web architecture, resource-oriented computing, social networking, the Semantic Web, data science, 3D graphics, visualization, scalable systems, security consulting and other technologies of the late 20th and early 21st Centuries. He is also a rabid reader, devoted foodie and has excellent taste in music. If pressed, he might tell you about his International Pop Recording career.
AI Crash Course
Brian Sletten
We've gone from slow but steady material advances in machine learning to a seeming explosion and ubiquity of AI-based features, products, and solutions. Even more, we're all expected to know how to adopt, use, and think about all of these magical new capabilities.
Equal parts amazing and terrifying, what you need to know about these so-called "AI" solutions is much easier to understand and far less magical than it may seem. This is your chance to catch up with the future and figure out what it means for you.
We will cover:
- A brief history of AI
- Machine Learning
- Deep Learning
- Deep Reinforcement Learning
- The Rise of Generative AI
- Large Language Models and RAG
- Multimodal Systems
- AI Reality Check
At the end of these sessions, you will be conversant with the major topics and understand better what to expect and where to spend your time in learning more.
Principal Data Scientist, Reputation
Dr. Carlos Kemeny is a Principal Data Scientist at Reputation and the founder of drumdata.ai, an AI and decision making research company. He is the former CEO of DrumCV and VP of artificial intelligence at Cinch, led data science at Weave Communications, and strategically advised several Fortune 250 C-Suites and senior executives while at Domo. Dr. Kemeny earned Dual-PhD and Master's degrees from Carnegie Mellon University, as well as an MBA and a Bachelor's degree in Mechanical Engineering from Purdue University. His dissertation on decision making and uncertainty informed his groundbreaking research on artificial intelligence and human decision making, which is the focus of his podcast "The AI Decision Guy".
Overcoming the AI Trust Gap
Carlos Kemeny
How do you create AI products that users will actually trust? In this session, you will participate in a groundbreaking research study on AI vs human decision making and learn about key findings gathered from over the last three years on how to develop and launch into production trustworthy AI products. Dr. Kemeny will then present case studies that compare and contrast AI product releases that garnered trust and those that didn't.
President, Bosatsu Consulting, Inc.
Brian Sletten is a liberal arts-educated software engineer with a focus on forward-leaning technologies. His experience has spanned many industries including retail, banking, online games, defense, finance, hospitality and health care. He has a B.S. in Computer Science from the College of William and Mary and lives in Auburn, CA. He focuses on web architecture, resource-oriented computing, social networking, the Semantic Web, data science, 3D graphics, visualization, scalable systems, security consulting and other technologies of the late 20th and early 21st Centuries. He is also a rabid reader, devoted foodie and has excellent taste in music. If pressed, he might tell you about his International Pop Recording career.
Security of ML and AI Systems
Brian Sletten
There is plenty of discussion about how machine learning will be applied to cybersecurity initiatives, but there is little conversation about the actual vulnerabilities of these systems themselves. Fortunately, there are a handful of research groups doing the work to assess the threats we face in systematizing data-driven systems. In this session, I will introduce to the main concerns and how you can start to think about protecting against them.
We will start with a discussion about building security into software in general and then discuss the research findings of the Berryville Institute of Machine Learning. They have conducted a survey of the literature on ML/AI/LLM systems and have identified a taxonomy of the most common kinds of attacks including:
* Adversarial examples * Data poisoning * Manipulation of online systems * Transfer learning attacks * Breaching data confidentiality * Undermining data trust
This will be a security-focused discussion. Only basic understanding of machine learning will be required.
Neal Ford
Distinguished Engineer
Thoughtworks, Inc
Neal Ford
Distinguished Engineer, Thoughtworks, Inc
Neal is a Distinguished Engineer at Thoughtworks, a software company and a community of passionate, purpose-led individuals, delivering technology to address the toughest challenges, all while seeking to revolutionize the IT industry and create positive social change. He speaks at many conferences.
The Intersection of Software Architecture & AI
Neal Ford
Is GenAI going to replace software architects? The short answer: no. The longer answer: it depends. This keynote delves into the tricky intersection of architecture and AI, how architects can use it effectively, and when they should avoid it like the plague. I also show some concrete techniques that developers and architects can use (today!) to leverage AI to help build fitness functions and other governance tools.
AI Developer Advocate, JetBrains
After having a career as a Data Scientist and Developer Advocate, Cheuk dedicated her work to the open-source community. Currently, she is working as AI developer advocate for JetBrains. She has co-founded Humble Data, a beginner Python workshop that has been happening around the world. She has served the EuroPython Society board for two years and is now a fellow and director of the Python Software Foundation.
What AI can do to enhance D&I in the community?
Cheuk Ting Ho
Like it or not, AI technology is going to be part of our life, just like any technology, it can be used to do good or harm. While we are conscious of this new technology, let’s look at how we can use it to our benefit and help with a constant battle in our community: diversity and inclusion.
## Target audience
Anyone who cares about the community and is curious about AI technology.
## Goal
To Explore the potential of our current AI technology and to educate the audience about AI technology so they will have the right expectations of the current technology.
## Outline
- Current AI technologies that have the potential to help - Increasing accessibility via AI - "Be my eyes" - Auto-translations - Lower the barrier to open source contribution with AI - coding assistance - better team tools - on the contrary, what we should be aware of - conclusion and Q&A
🎦
Multi Modal Models
Learn to take your machine learning models to work with and generate multimodal models like text, images, audio, video, and more. See how you can create and use models that can combine data from different modalities to bring greater capabilities to your applications.
🎦 Hypermedia APIs and the Future of AI Agentic Systems
Holistic Software Architect, Carducci Inc
Michael Carducci is a seasoned IT professional with over 25 years of experience, an author, and an internationally recognized speaker, blending expertise in software architecture with the artistry of magic and mentalism. His upcoming book, "Mastering Software Architecture," reflects his deep understanding of the multifaceted challenges of building resilient, effective software systems and high-performing teams. Michael's career spans roles from individual contributor to CTO, with a particular focus on strategic architecture and holistic transformation.
As a magician and mentalist, Michael has captivated audiences in dozens of countries, applying the same creativity and problem-solving skills that define his technology career. He excels in transforming complex technical concepts into engaging narratives, making him a sought-after speaker and emcee for tech events worldwide.
In his consulting work, Michael adopts a holistic approach to software architecture, ensuring alignment with business strategy and operational realities. He empowers teams, bridges tactical and strategic objectives, and guides organizations through transformative changes, always aiming to create sustainable, adaptable solutions.
Michael's unique blend of technical acumen and performative talent makes him an unparalleled force in both the tech and entertainment industries, driven by a passion for continuous learning and a commitment to excellence.
Hypermedia APIs and the Future of AI Agentic Systems
Michael Carducci
The age of hypermedia-driven APIs is finally upon us, and it’s unlocking a radical new future for AI agents. By combining the power of the Hydra linked-data vocabulary with semantic payloads, APIs can become fully self-describing and consumable by intelligent agents, paving the way for a new class of autonomous systems. In this session, we’ll explore how mature REST APIs (level 3) open up groundbreaking possibilities for agentic systems, where AI agents can perform complex tasks without human intervention.
You’ll learn how language models can understand and interact with hypermedia-driven APIs, and how linked data can power autonomous decision-making. We’ll also examine real-world use cases where AI agents use these advanced APIs to transform industries—from e-commerce to enterprise software. If you’re ready to explore the future of AI-driven systems and how hypermedia APIs are the key to unlocking it, this session will give you the knowledge and tools to get started.
🎦 Multimodal Spring AI - Building voice, image generation, and vision into your Spring applications
Principal Engineer, Habuma
Craig Walls is a Principal Engineer, Java Champion, Alexa Champion, and the author of Spring AI in Action, Spring in Action, Spring Boot in Action, and Build Talking Apps. He's a zealous promoter of the Spring Framework, voice application development, and generative AI. When he's not slinging code, Craig is planning his next trip to Disney World or Disneyland and spending as much time as he can with his wife, two daughters, 1 bird and 3 dogs.
Multimodal Spring AI - Building voice, image generation, and vision into your Spring applications
Craig Walls
Most of the buzz around Generative AI has been how it is able to understand and respond to natural language prompts. But largely, those prompts have been typed in by a user and the responses have come back in textual form.
While humans often communicate with each other in a similar way via text messages and emails, natural interaction takes place across many modes of communication, including talking, hearing, seeing, and showing.
In this session, you'll see how to add sight and sound to your Spring AI applications. You'll learn how to build applications that can both talk and hear what your users say as "see" what your users show them (via images) and produce responses in graphic form.