Software Architecture Superstream: Software Architecture and the Age of Agentic AI
Published by O'Reilly Media, Inc.
Rethink software systems and architectural trade-offs for autonomous agents
Every time a change happens in AI, it changes intersections in architecture. While traditional AI systems are often static and rule-based, designed to perform specific tasks based on predefined inputs, agentic AI has introduced autonomous systems that can set goals, create plans, and execute multistep tasks with minimal human intervention. How does this shift impact the way we design and build software systems?
Join us for a deep dive into the evolving world of software architecture in the age of agentic AI. It isn’t just about adding a new component to your tech stack; it’s about rethinking the entire system. Your host, Neal Ford, leads an examination into how this shift from static AI to goal-oriented agents is impacting software architecture in critical areas. Expert guest speakers provide insights into how these intelligent agents can function as the new microservices, enabling systems that are more dynamic, scalable, and resilient.
What you’ll learn and how you can apply it
- Explore the architectural considerations you need to keep in mind, given the nature of autonomous AI agents
- Understand the technical shifts necessary to transform static data into contextually rich, traceable, and actionable foundations for enterprise automation
- Gain practical insights into using event-driven designs and standardized protocols to connect complex AI workflows with real-world business tools
Recommended follow-up
- Read Data Architecture (early release book)
- Read Building Resilient Distributed Systems (early release book)
- Take Architecture as Code (live online course with Neal Ford)
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.
Fireside Chat with Sam Newman: Architecting for AI (35 minutes)
Sam Newman, author of the best-selling Building Microservices, joins Neal Ford for a discussion on navigating the architectural questions and practical realities of the agentic shift. Discover how agentic AI introduces background uncertainty and why microservices make a lot of sense for AI.
Making Your Data Ready for Agentic AI – Pramod Sadalage and Premanand Chandrasekaran (35 minutes)
As the industry shifts from simple chatbots to autonomous AI agents, the bottleneck is no longer the model—it’s the architecture of your data. Agentic workflows require data that’s not just searchable, but actionable, traceable, and contextually rich, and that means building a foundation where agents can retrieve the right context, trust it, and act on it safely. This is what turns AI “answers” into real automation. Join Thoughtworks experts Pramod Sadalage and Premanand Chandrasekaran to explore ways of ensuring your data is ready for agentic AI.
Break (5 minutes)
Designing Scalable Agent-Based Service Architectures – Rob Reid (Sponsored by Cockroach Labs) (30 minutes)
With more agentic workflows moving into production, businesses must rethink not just application logic but also the underlying database layer and its scalability. Rob Reid, technical evangelist at Cockroach Labs, examines an agentic fraud detection system to explore what AI-ready scale looks like in practice. You’ll see how three coordinated agents—anomaly detection, reasoning, and notifications—operate continuously under load, use vector embeddings and L2 distance to identify anomalous transactions, fetch real-time context, reason about risk, and trigger customer notifications. You’ll also learn about the database architecture this model needs in order to handle high concurrency, maintain strong consistency, and unify relational and vector data without brittle orchestration or batch pipelines.
This session will be followed by a 30-minute Q&A in a breakout room. Stop by if you have more questions for Rob.
Harnessing Event-Driven and Multi-Agent Architectures for Complex Workflows in Generative AI Systems – Mary Grygleski (35 minutes)
Generative AI can struggle with the complexity of modern business workflows. However, event-driven architectures and multi-agent systems offer a solution by providing real-time processing, decentralized decision-making, and adaptability. Mary Grygleski, global (Western Hemisphere) vice president at The AI Collective, explores these approaches to designing and implementing complex, highly adaptive, efficient, and scalable generative AI workflows, covering theoretical foundations and practical benefits.
Break (5 minutes)
Simplifying Context Engineering for AI Agents in Production – Cornelia Davis (35 minutes)
Context engineering is critical for creating useful, production-ready agents. Cornelia Davis, developer advocate for Temporal, addresses common context engineering challenges and demonstrates how you can simplify their resolution, giving you practical strategies for building agents that are more reliable, focused, and adaptable in real-world scenarios.
Building Enterprise AI Agents with Model Context Protocol – Cedric Clyburn and Peter Double (35 minutes)
Connecting LLMs to tools across an enterprise has traditionally required complex, custom code for every integration. Now, however, Model Context Protocol (MCP) can unlock the business potential of agentic AI. Peter Double, principal product manager, and Cedric Clyburn, senior technical marketing manager at Red Hat, unpack how MCP brings portability, efficiency, and governance to AI agents, and how the company is building a path to innovate faster with a full lifecycle approach.
Closing Remarks – Neal Ford (5 minutes)
Neal Ford closes out today’s event.
Your Hosts and Selected Speakers
Neal Ford
Neal Ford is an independent software consultant, best-selling author, speaker, and innovator in building concrete verification mechanisms for software architecture, for humans or agents. He’s an internationally recognized expert on software development and delivery, especially at the intersection of agile engineering techniques and software architecture. Neal has authored magazine articles, nine books (and counting), and dozens of video presentations, and has spoken at hundreds of developers’ conferences worldwide. His topics include software architecture, continuous delivery, functional programming, cutting-edge software engineering, and improving technical presentations. Check out his web site at Nealford.com.
Sam Newman
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 (now in its second edition) and Monolith To Microservices, both from O’Reilly, and is also an experienced conference speaker.
Pramod Sadalage
Pramod Sadalage is a distinguished engineer at Thoughtworks, where he usually takes on clients with particularly challenging data needs that require new technologies and techniques. In the early 2000s, he developed techniques to allow relational databases to be designed in an evolutionary manner based on version-controlled schema migrations. His latest book, _Data Architecture _(coauthored with Premanand Chandrasekaran), is in early release on the O'Reilly platform.
Premanand Chandrasekaran
Premanand Chandrasekaran serves as market tech director at Thoughtworks. He’s a change agent with over 25 years of experience leading software teams and helping businesses tackle mission-critical challenges. His latest book, Data Architecture (coauthored with Pramod), is in early release on the O’Reilly platform.
Rob Reid
Rob Reid is Cockroach Labs’ technical evangelist and a software developer from London, England. He has written backend, frontend, and messaging software for law enforcement, travel, finance, commodities, sports betting, telecoms, retail, and aerospace industries. He’s the author of Practical CockroachDB: Building Fault-Tolerant Distributed SQL Databases (Apress) and Understanding Multi-Region Application Architecture and CockroachDB: The Definitive Guide, second edition (O’Reilly), and he has two CockroachDB tattoos.
Mary Grygleski
Mary Grygleski is the vice president of Global for the Western Hemisphere at the AI Collective, overseeing the health and growth of the community in North and Latin Americas. She started her career in software engineering and has deep interest in distributed systems, which cover all spectrums in the computing world. She is also very passionate about tech advocacy and community work, and has been leading the Java users group in Chicago since 2015. She is recognized as a Java Champion and an Oracle ACE Associate.
Cornelia Davis
Cornelia Davis is principal developer advocate for Temporal, where she’s helping drive the expansion of the “durable execution” distributed systems paradigm. She’s also the author of Cloud Native Patterns: Designing Change-Tolerant Software. Cornelia has spent her career at the forefront of technological innovation, starting with image processing algorithm development, moving to web-centric computing in the late 1990s, and then working in cloud native software and DevOps platforms for more than a decade.
Cedric Clyburn
Cedric Clyburn, senior developer advocate at Red Hat, is an enthusiastic software developer with a background in Kubernetes, DevOps, and container tools. Focused on open source software, he both contributes to projects (e.g., Podman, vLLM) and speaks at conferences such as Devoxx, WeAreDevelopers, The Linux Foundation, and more. Cedric also spends (too much) time creating video and written content that helps developers learn new topics in emerging technologies, with over 2M+ views online.
Peter Double
Peter Double is an AI principal product manager at Red Hat.
