Introduction to the Agent MCP Workshop: Building Your Own Java-based MCP Server

The Agent MCP Workshop is an instructor-led series designed to guide participants through developing a Java‑based server implementing the Model Context Protocol (MCP). This introduction sets expectations and provides orientation for the learning journey, including prerequisites, workshop structure, and branch-based lesson flow. Participants are encouraged to complete a pre-workshop setup (via 00-setup.md) before class to ensure their environment is ready. The workshop is structured across successive branches—starting with 01-chapter, each representing a progressive lesson where learners will build components of an MCP server from scratch. While self-study is possible, success depends on active instruction and group participation. The introduction also outlines workshop objectives, teaches working with Java’s standard libraries, JSON‑RPC messaging, tool registration, agent integration, and hands-on debugging techniques like STDIO-based communication and protocol-level routing. By setting these foundations, the introduction prepares learners to embark on a hands-on path toward building fully functioning, testable MCP-compatible agents and tools.

AI Assisted Coding: Navigating the Strengths, Challenges, and Future of Coding Assistants

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.

Getting Groovy: AI-Powered Spock Testing

Spock is a testing and specification framework for Java and Groovy applications. What makes it stand out from the crowd is its beautiful and highly expressive specification language. Thanks to its JUnit runner, Spock is compatible with most IDEs, build tools, and continuous integration servers. Inspired by JUnit, jMock, RSpec, Groovy, Scala, Vulcans, and other fascinating life forms, Spock brings a unique flavor to testing.

Spock uses the Abstract Syntax Tree (AST) in Groovy, which removes many of the ceremonial handcuffs that come with other frameworks, creating a fluid test domain-specific language.

But what if we could take Spock’s capabilities even further? By integrating AI into our testing processes, we can write better tests with AI—enhancing not only the efficiency but also the intelligence of our test suites. AI can assist in generating test cases, identifying edge cases that might be overlooked, and even optimizing test performance by analyzing past test runs.

In this talk, I will limit slides and opt for live code to show off the power of Spock combined with AI assistance. I’ll demonstrate how AI tools can help write more robust and comprehensive tests within the Spock framework. Join me in going boldly where many developers are heading by learning not just the basics of the Spock Framework, but also how to leverage AI to elevate your testing to the next level.

Codebase Resurrection: Revive and Refactor with AI

Is your codebase in need of a major overhaul? Do you find yourself wrestling with tangled code, uncertain about the consequences of each refactor? Join us at this Java conference session to discover how AI can be your secret weapon in the battle against subpar code.
In this enlightening talk, our seasoned Principal Software Developer will guide you through the transformative journey of leveraging Codium.AI to bring your codebase back to life. We'll demonstrate the incredible power of this AI plugin, which combines the best practices and methodologies from industry experts with the precision of artificial intelligence.
You'll learn how to harness Codium.AI's capabilities to:
Analyze Code Health: Understand the current state of your codebase and identify areas in need of improvement.
AI-Powered Testing: Utilize AI-driven testing to gain confidence in your refactoring efforts, reducing the risk of introducing new bugs.
Refactor with Precision: Apply expert-recommended refactorings to untangle complex code structures and improve maintainability.
Measure Success: Evaluate the impact of your refactorings and track improvements in code quality and performance.
By the end of this session, you'll be equipped with the knowledge and tools to breathe new life into your codebase, making it more efficient, robust, and future-proof. Don't miss this opportunity to revolutionize your coding practices and elevate your software architecture to new heights with Codium.AI. Join us and embark on your journey towards code excellence!

Inside MCP: Live Protocol Messages, Real-Time Flows, and Smarter Agents

You’ve heard the buzz — now roll up your sleeves and build with it. In this hands-on workshop, you’ll learn exactly how the Model Context Protocol (MCP) works — and you’ll write your own MCP server tool from scratch, then author an Agent that uses it to deliver real-time, context-aware help right inside your dev flow.

We’ll break down the raw MCP protocol step by step:
• How it streams context between your IDE and Agents
• How messages are structured and exchanged
• How to wire up an MCP Client to talk to your new tool

By the end, you’ll not only understand the protocol — you’ll have built a working MCP server tool and your own Agent that plugs into it to automate tasks, provide better suggestions, and boost your productivity.

Bring your curiosity — and your laptop — because you’ll walk away with practical code, a working prototype, and the confidence to build and extend your own MCP-powered tools and Agents.

bring your command line, IDE.
Attendees will understand the fundamental design and flow of the Model Context Protocol — how it passes real-time context between developer tools and intelligent Agents, and why that matters for productivity.

The New Review Burden: More Code Generated Than Written — Now What?

As AI-assisted coding and automated generation tools pump out more lines than human developers ever could alone, the responsibility to catch subtle bugs and maintain quality has shifted heavily to the review stage.

In this talk, we’ll walk through practical ways to adapt your review process for a world where more code is generated than written by hand. We’ll cover how to establish clear team guidelines and require structured artifacts with every pull request — not just a list of files changed, but well-organized summaries that categorize and group code modifications by purpose and impact.

We’ll discuss how to classify PR types — from bug fixes to new features — and define levels of effort so reviewers can gauge how much time and scrutiny each change deserves. As tools generate more of our code, we also need AI and automated helpers to reason through those changes, highlight potential security concerns, and map out how modifications ripple through the codebase.

Finally, we’ll look at the non-negotiables: setting up static analysis gates (linters, PMD, SpotBugs, Checkstyle), enforcing agreed-upon quality metrics, and ensuring unit tests and coverage thresholds are met before code ever hits the main branch.

You’ll leave with a blueprint to review smarter and faster — and catch the bugs that AI might sneak in.

PR Pitfalls: What I Wish I Knew as a Junior Developer

Starting a new job as a junior developer is exciting — until you hit your first pull request. In this talk, I’ll share the common (and painful) pitfalls I wish I had avoided when submitting PRs early in my career. From underestimating the importance of clear commit messages, to neglecting test coverage, to misunderstanding review feedback — we’ll walk through real lessons learned the hard way.

But this isn’t just for juniors. In today’s world of AI-powered development, there are powerful ways to avoid these same mistakes — and even seasoned, salty developers can pick up a few nuggets to up their game. We’ll explore practical ways to use AI tools to check your PRs, tighten up your code, generate better documentation, and make your review process smoother and faster — so you can spend less time fixing rookie mistakes and more time shipping quality code.

Whether you’re starting your first dev role or you’ve been merging PRs for years, this talk will help you level up your workflow and see how AI can make your developer life just a little bit easier.