Skip to Content
View all events

Teach Your Agents About Software Architecture

Published by O'Reilly Media, Inc.

Intermediate content levelIntermediate

Help guide your agents to build properly architected code

What you’ll learn and how you can apply it

  • Learn how to implement the concepts of architecture as code in your work with agentic AI

Course description

Agentic AI shows new capabilities in software architecture, including the ability to work toward a solution, as long as deterministic constraints exist. Developers and architects who want to build ways for agents to determine success require a deterministic method of defining these important constraints. This is where architecture as code can be applied to agentic AI. Neal Ford shows you how to use AaC to help build foundational constraints that, in turn, help guide agents to build properly architected code.

Architecture as code starts with the concept of describing in code all the ways that software architecture intersects with other parts of the software development ecosystem—data, engineering practices, team topologies, and more—as a way of creating a fast feedback loop for architects to react to changes in architecture. In other words, documenting the architecture through code, defining the structure and constraints we want to guide the implementation through. This capability is useful for developers, and it’s useful for agents.

This live event is for you because...

  • You’re a software engineer or architect.
  • You work with agents.
  • You want to become an architect or engineer who works with AI.

Prerequisites

  • An understanding of core architectural concepts

Recommended follow-up:

Schedule

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

What (20 minutes)

  • Presentation: From prompt to context engineering; setting foundational rules for agentic code generation

How (70 minutes)

  • Presentation: Building deterministic guardrails for agentic behavior; architectural fitness functions; scope; platforms; LLM as an interpolator—generating fitness functions; Architecture Definition Language (ADL) defined; examples; alternatives; MCP and governance mesh; building implementation constraints; code quality, structure, constraints/governance
  • Hands-on exercises: Generate concrete fitness functions; Make the Grade guardrails
  • Break

Where (135)

  • Presentation: Engineering practices; controlling version control; preventing cheating in mono-repos; preventing code duplication in repo-per-service; preventing churn; architecture quantum coupling; handing problems in distributed architectures; data consistency; referential integrity; cascading updates/deletes; controlling data coupling; architecture as code → infrastructure as code; governing generated infrastructure; ADL alternatives
  • Hands-on exercise: How much copy/paste is OK?; limit static and dynamic coupling; translate CALM to ADL; Math the Grade data integrity
  • Break
  • Presentation: Team topologies; how to tell if you have the correct distribution of agents/team members; building process feedback loops; enterprise architecture; global governance; governance strategies; centralized; prescriptive; classic alternative; decentralized; distributed; durable interface; adapting governance to the AI age

Your Instructor

  • 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 eight books (and counting), a number of magazine articles, and dozens of video presentations (including a video on improving technical presentations) and spoken at hundreds of developers conferences worldwide. His topics of interest include software architecture, continuous delivery, functional programming, and cutting-edge software innovations. Check out his website, Nealford.com.

Skills covered

  • Software Architecture
  • Generative AI
  • Object-Oriented Architecture
  • Architectural Patterns