Skip to content
  • Sign In
  • Try Now
View all events
Software Architecture

Software Architecture Superstream: Software Architecture in the Age of AI

Published by O'Reilly Media, Inc.

Beginner to advanced content levelBeginner to advanced

Discover how AI impacts software architecture

We're moving toward a future where most software architectures will need to support the use of AI, whether AI is the focus of the business or not. So what do software architects need to consider when designing new systems (or evolving existing architectures) to manage the large amounts of data required for machine learning, all while meeting the needs of the business?

Join us to discover how AI can impact software architecture and how you can use it in your architectural processes right now. You’ll learn how to use AI for system design, how to architect systems to prepare for AI, and more. You'll find out how to use AI to support your own communication and collaboration with technical and business stakeholders. If you’re a software architect looking to stay one step ahead, this session is for you.

What you’ll learn and how you can apply it

  • Understand how AI changes your role as a software architect and the new challenges that may arise along the way.
  • Explore the realities of integrating LLMs into your products and ensure performance is sufficient for production.
  • Understand how to build your own RAG architectures and incorporate RAG into existing event-driven architectures.

Recommended follow-up:

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Introduction – Neal Ford (5 minutes)

  • Neal Ford welcomes you to the Software Architecture Superstream.

Architecture and (Gen)AI – Rebecca Parsons (35 minutes)

  • As AI and GenAI become more prevalent in organizations, we need to consider the architectural implications. Rebecca Parsons, Thoughtworks CTO Emerita, takes you through significant architectural issues at the hardware, model, infrastructure, tools, and application layer. You’ll also explore how AI changes the role of architects and the new challenges that may arise along the way.

Architecting Scalable AI Systems with RedisVL: Optimizing RAG Pipelines – Akarsh Verma (35 minutes)

  • RedisVL is a Python library that simplifies using Redis as a vector database and LLM cache for building retrieval-augmented generation (RAG) architectures. It offers high performance, ease of use, and robust index management, making it an ideal tool for RAG implementations. Senior solution architect and product manager Akarsh Verma helps you understand how to design and build a RAG architecture using RedisVL, exploring key implementation details and best practices.

Break (5 minutes)

Integrating LLMs into Your Product: Considerations and Best Practices – Denys Linkov (35 minutes)

  • AI projects often end up in proof-of-concept purgatory, and many companies struggle to ensure that LLM performance is sufficient for production. Denys Linkov, head of ML at Wisedocs and advisor at Voiceflow, reflects on Voiceflow's journey and shares key lessons learned incorporating GenAI into its product offering.

Using Generative AI in Event-Driven Architectures – Adam Bellemare (35 minutes)

  • How can you begin to integrate elements of generative AI into your event-driven architectures? Adam Bellemare, author and principal technologist at Confluent, shows you how to add chatbots or prediction engines to your architecture using event-driven supported RAG. You’ll explore streaming-based RAG and understand how to provide essential context for GenAI queries.

Break (5 minutes)

Emerging Architectures of AI Applications – Gad Benram and Gabriel Gonçalves (35 minutes)

  • Modern AI applications have come a long way just since 2023, when development was dominated by retrieval-augmented generation (RAG) and chain-based methodologies. Today, these applications leverage the latest LLM research, moving toward autonomous agents that incorporate reasoning, planning, and collaboration. Gad Benram, cofounder and CTO at TensorOps, and Gabriel Gonçalves, solution architect at TensorOps, present the core elements of modern AI application architectures, discuss what these components entail, and demonstrate their implementation using a variety of technologies, databases, platforms, and models in production-grade AI solutions.

Session to Come (35 minutes)

  • Please check back for more information.

Closing Remarks – Neal Ford (5 minutes)

  • Neal Ford closes out today’s event.

Your Hosts and Selected Speakers

  • Neal Ford

    Neal Ford is a director, software architect, and meme wrangler at Thoughtworks, a software company and a community of passionate, purpose-led individuals who think disruptively to deliver technology to address the toughest challenges, all while seeking to revolutionize the IT industry and create positive social change. He’s an internationally recognized expert on software development and delivery, especially in the intersection of Agile engineering techniques and software architecture. Neal’s authored several books, a number of magazine articles, and dozens of video presentations (including a video on improving technical presentations) and spoken at hundreds of developer conferences worldwide. His topics of interest include software architecture, continuous delivery, functional programming, and cutting-edge software innovations. Check out his website, Nealford.com

    Xlinksearch

  • Rebecca Parsons

    Rebecca Parsons is Thoughtworks' CTO Emerita. She has more years of experience than she’d like to admit in technology and large-scale software development. She recently coauthored the book Building Evolutionary Architectures with colleagues Neal Ford and Pat Kua. Before ThoughtWorks she was an assistant professor of computer science at the University of Central Florida, after completing a Director's Postdoctoral Fellowship at the Los Alamos National Laboratory.

  • Akarsh Verma

    Akarsh Verma is a passionate senior solution architect and product manager who loves taking on complex challenges and designing impactful systems. His expertise covers product design, architecture, MLOps, system design, cloud solutions, GenAI, and LLMs. He’s always learning and growing in this ever-evolving tech world. When he’s not deep in code, you’ll find him enjoying a good book, getting lost in an exciting comic, or savoring a perfectly brewed cup of coffee.

  • Denys Linkov

    Denys Linkov is the head of ML at Wisedocs, an advisor at Voiceflow, and a sessional lecturer at the University of Toronto. He's worked with 50+ enterprises in their AI journey, and his GenAI courses have helped 200,000+ learners build key skills. He's worked across the AI product stack, building key ML systems, managing product delivery teams, and working directly with customers to implement best practices.

  • Adam Bellemare

    Adam Bellemare is a principal technologist at Confluent. He’s also the author of Building Event-Driven Microservices and Building an Event-Driven Data Mesh, both published by O'Reilly. Previously, he worked in data platform engineering at Shopify, Flipp, and BlackBerry.

  • Gad Benram

    Gad Benram is cofounder and CTO at TensorOps, designing and delivering large-scale, production-grade ML and AI solutions for global organizations. His work spans from implementing cutting-edge LLM architectures to ensuring highly reliable enterprise-level deployments at companies like Notion and Infosys. Gad is both a Google Developer Expert in AI and an AWS SageMaker Black Belt, reflecting his deep expertise and thought leadership in the AI and ML ecosystem.

  • Gabriel Gonçalves

    Gabriel Gonçalves is a solution architect at TensorOps specializing in implementing end-to-end solutions involving traditional ML, time series forecasting, and generative AI. He leads AI initiatives in cybersecurity and software supply chain domains and is a recognized contributor to tech communities such as Neptune. Gabriel is one of the earliest contributors to LLM Studio, a leading open source AI proxy solution.