Software Development Superstream Generative Ai for Code Modernization O’ Reilly Live Events
Software Development Superstream: Generative AI for Code Modernization - O’Reilly Live Events #
Excerpt #
Accelerate the optimization and enhancement of existing systems
[
View all events
]( https://www.oreilly.com/live-events/?page=1)
Published by O’Reilly Media, Inc.
Accelerate the optimization and enhancement of existing systems
Changing code manually is tiring and time-consuming, but modernizing applications is essential maintenance for successful software. Generative AI can help accelerate the process by making your code more efficient and easier to maintain and change—ensuring that your applications support the latest features.
Our panel of experts shows you how to use generative AI to benefit your codebase. You’ll learn how to incorporate AI tools into your workflow to enhance common development processes, from measuring the quality of your code to refactoring it to measuring it again to prove that it’s not only more elegant but also more cost-effective.
What you’ll learn and how you can apply it #
- Use generative AI tools to modernize your legacy systems
- Identify patterns in LLM outputs to ensure effective and efficient refactoring
- Apply an AI development lifecycle to existing systems
Recommended follow-up:
- Read Generative AI for Software Development (early release book)
- Take Using LLMs for Software Engineering (live course with Chelsea Troy)
- Read AI Engineering (book)
Schedule #
The time frames are only estimates and may vary according to how the class is progressing.
Introduction – Sam Newman (5 minutes)
- Sam Newman welcomes you to the Software Development Superstream.
Fireside Chat with Michael Feathers and Sam Newman (40 minutes)
- Michael Feathers, renowned software expert and author of Working Effectively with Legacy Code, joins Sam Newman to discuss the evolving world of AI assistants in software development. Michael and Sam share ways that AI can help developers explain code, identify potential issues, generate tests, and explore new possibilities.
Evaluating Patterns in LLM Outputs – Chelsea Troy (40 minutes)
- How does the way that LLMs function intersect with their ability to solve programming problems? Join Chelsea Troy, machine learning operations engineer at Mozilla, for a primer on what LLMs tend to do well, where they tend to struggle, and what that means for practitioners in an LLM-enabled world.
Break (5 minutes)
Modernizing Legacy Software with GenAI: Insights from the Trenches – Jurre Brandsen (40 minutes)
- There is no AI developer without the “developer.” Info Support software engineer Jurre Brandsen takes you through the lessons his team learned as they modernized their software using generative AI. You’ll discover how to best process input data, use prompts and “the human in the loop” effectively, get better results by using Python as an intermediate language, and more.
Tackling Enterprise Code Modernization with AI – John Feeney (Sponsored by Tabnine) (30 minutes)
- AI is transforming enterprise code modernization—but success hinges on context. John Feeney, principal architect at Tabnine, delves into how the synergy of LLMs, AI agents, and retrieval-augmented generation enables refactoring of monolithic architectures and outdated languages while mitigating technical debt. Discover how contextual AI bridges the gap between generic coding knowledge and your organization’s unique standards, turning AI assistants into senior engineers that align with your team’s expectations throughout the SDLC. Unlock actionable strategies to modernize enterprise systems with scalability, maintainability, and innovation at the forefront.
- This session will be followed by a 30-minute Q&A in a breakout room. Stop by if you have more questions for John.
Break (5 minutes)
A Smorgasbord: AI For Systems Modernisation – Birgitta Böckeler (40 minutes)
- Birgitta Böckeler, global lead for AI-assisted software delivery at Thoughtworks, explores the emerging applications of generative AI in systems modernization. Moving beyond code generation to a wider range of tasks, she presents a selection of both real-world and speculative use cases to give you a more nuanced understanding of AI’s potential, with insights into promising applications and areas where AI may be less effective.
Closing Remarks – Sam Newman (5 minutes)
- Sam Newman closes out today’s event.
Feb 11 #
1pm-5pm Brasilia Standard Time
31 Spots Remaining
or sign in.
Your Hosts and Selected Speakers #
Sam Newman is a technologist focusing on the areas of cloud, microservices, and continuous delivery—three topics which seem to overlap frequently. He provides consulting, training, and advisory services to startups and large multinational enterprises alike, drawing on his more than 20 years in IT as a developer, sysadmin, and architect. Sam is the author of the best-selling Building Microservices and Monolith to Microservices, both from O’Reilly, and is also an experienced conference speaker.
Michael Feathers is the founder and director of R7K Research & Conveyance, a company specializing in software and organization design. He’s also the author of the book Working Effectively with Legacy Code (Prentice Hall, 2004).
Chelsea Troy leads the machine learning operations team at Mozilla. She also teaches in the Master’s Program in Computer Science at the University of Chicago. Her online workshop, Fundamentals of Technical Debt, is available On Demand through the O’Reilly platform, and she also gives live courses about machine learning, large language models, and product thinking.
Jurre Brandsen is a software engineer at Info Support. Jurre has a particular interest in building scalable, high-performance applications within .NET development and artificial intelligence. During his studies, he developed a real-time data processing application using .NET and implemented machine learning algorithms to optimize system performance, sparking his interest in the power of distributed technologies. His goal is to master the intricacies of software engineering, continually seeking opportunities to integrate AI in practical, impactful ways that drive innovation and add value.
John Feeney is a principal architect within the CTO Office at Tabnine. Prior to helping Tabnine’s customers accelerate their software development cycles through the use of AI, he worked with various APM and DevOps tooling vendors to help drive development and operational efficiencies. He is based in Dublin, Ireland.
Birgitta Böckeler is global lead for AI-assisted software delivery at Thoughtworks and a software developer, architect, and technical leader with 20 years of experience. As a software delivery consultant, Birgitta has had the opportunity to see many organizations and teams succeed, or fail, at delivering valuable software.
Associated roles #
- Android developer
- Backend developer
- Business analyst
- Business intelligence analyst
Skill covered #
Generative AI