Name: AI Coding Summit
Start: 2025-10-23T14:00:00.000Z
End: 2025-10-24T17:00:00.000Z

Stefan Wille

Innocencia Ndembera

David Pugh

Jennifer

Emerson Marini

Habib Hinn

Ivan Almasi

Wiktoria Van Harneveldt

Ludovic Bouges

Anmol Vashistha

Behrouz Pooladrak

Vitor Barbosa

Evan Charalampidis

Maq Said

Shivam Arora

Karyna Bunta

Giorgos Patelis

Boris Karaivanov

Paul Greetham

Michael Chiche

Filip Michalowski

Ryan Valle

Gerjan Kempkens

Jim Hoffman

Daniel

Petr Vocelka

Denis Bratchikov

BitGiorgio

Rohid Safi

Nalliappan Ganeshan

Vikram Thalithaje

Fernando Eguílaz

Vedat Erenoglu

Matteo Bruno

Sub Agent Context Sharing: How to Enable Effective Sub Agents for Coding

 Zhou Jason

AI coding assistants are great at completing small tasks or features. However, what do you do when you are working with more complex code bases, and you need to build in-depth features that need upfront planning?This talk explores spec-driven development as a solution to this problem. I'll show you how modern AI coding assistants (like Kiro) can help break down complex tasks into three distinct phases. We'll look at the real-world tradeoffs of this approach, and most importantly and how you can use it in your own projects right away.

Using Spec-Driven Development for Agentic Coding

Erik Hanchett

This workshop introduces Context Engineering - a simple yet structured approach to getting consistent, high-quality results from AI coding assistants. You'll learn how to move beyond basic prompting to create comprehensive workflows to give your AI coding assistants all the architecture, best practices, project rules, code examples, and validation processes it needs to get the job done effectively. Through hands-on exercises with Claude Code, we'll demonstrate how proper Context Engineering unlocks a whole new level of agentic engineering while teaching practical techniques, templates, and best practices that help AI assistants understand your project standards and deliver production-ready code consistently.

Advanced Claude Code Techniques: Agentic Engineering With Context Driven Development

 Cole Medin

This talk shows how to wire agentic workflows into modern CI/CD so code gets safer and faster to prod: LLM code review as a first pass, automated remediation suggestions, and swarm-style orchestration for follow-ups. You’ll see what actually works today with Copilot Code Review, CodeQL Autofix, Semgrep Assistant, and agent frameworks like LangGraph or AutoGen, plus how to gate merges with lightweight, automated evaluations.

Agentic CI/CD: from Pull Request to Production without the Paper Cuts

Chaitanya Rahalkar

We've all heard about prompt engineering. But now with the emergence of context engineering you may be scratching your head about what the difference is. The reality is that to build reliable agents, we need to use all tools in our context toolbox to ensure they provide accurate responses in the correct format.Let's dive into the world of context engineering, and understand the elements of context that we can tune and tweak to build more reliable AI agents and associated systems.

Crafting Intelligent Agents with Context Engineering

Carly Richmond

Join a focused 2-hour session covering MCP's purpose, architecture, hands-on server implementation, and future directions. Designed for developers and system architects aiming to integrate contextual data with ML models effectively. Agenda:- Introduction &amp; Why MCP? Key challenges MCP solves and core benefits.- Architecture Deep Dive: components, interactions, scalability principles. - Building Your Own MCP Server: guided walkthrough with code snippets and best practices; live demo or code review.- Future of MCP Developments: potential enhancements, emerging trends, real-world scenarios. Key Takeaways:- Clear understanding of MCP's rationale.- Insight into design patterns and scaling considerations.- Practical steps to implement a prototype server.- Awareness of upcoming trends and how to apply MCP in projects.

Model Context Protocol (MCP) Deep Dive: 2-Hour Interactive Workshop

Stepan Suvorov

In this workshop, I’ll guide participants through a process for building full-stack applications using Cursor. We’ll cover setting up Cursor workflows, including rules, commands, and custom modes, to streamline development. We will use Cursor to draft PRDs, database schema, etc and a simple SOW. We’ll turn notes into actionable checklists to guide the build, connecting the front end, API, and database.Additionally, we’ll create workflows for debugging, testing, reviewing, and fixing the app while reducing hallucinations with precise prompts. The session will also include a security review workflow and techniques for applying prompts to achieve a modern UI design. Attendees will leave with a functioning app on their machine and a reusable development process.

How to Build Full-Stack Apps Using Cursor

 Shrey Shah

Discover how to use Docker to package, ship, and run AI tools built on the Model Context Protocol (MCP). Learn how to create reproducible MCP servers and clients, integrate them into developer workflows, and scale them in production — from local dev to agentic CI/CD pipelines.

Docker MCP: Packaging & Deploying AI Tools with Model Context Protocol

Kristiyan Velkov

AI-powered code review promises faster development cycles, but making it work in production requires more than just plugging in an LLM. This talk explores best practices, pitfalls, and real-world lessons from building AI-driven review and refactoring pipelines in enterprise systems. Attendees will learn how to evaluate quality, avoid false positives, and integrate AI review safely into CI/CD workflows.

Code Review with LLMs: From Pitfalls to Production-Ready Pipelines

Ganesh Divekar

Workshop Objective:Show how teams can go from AI-generated UI to live production components in under an hour.Workshop Agenda:Part 1: Kickoff &amp; Setup <ul><li>- Quick intro to the Pluggable AI method</li><li>- Walk through a real example already running in production</li><li>- Align on the selected AI/visual tool (Claude, Gemini, etc.)</li><li>- Choose 1–2 UI components to work with</li><li>- Define what’s needed to make the component pluggable</li><li>- Select the host app </li></ul>Part 2: Generate the Component <ul><li>- Use the selected AI tool to generate the UI component</li><li>- Myop team helps ensure it fits integration guidelines (structure, format)</li></ul>Part 3: Integration Preps<ul><li>- Identifying where the component connects (logic hook)</li><li>-Review generated component and prepare for connection</li></ul>Part 4: Plug It Live <ul><li>- Plug the component into the live app using Myop's open source</li><li>- Optional: test versioning, A/B testing, segmentation, gradual rollout</li></ul>Part 5: Wrap-Up<ul><li>- Recap effort vs. outcome</li><li>- Q&amp;A  </li></ul>

From Prompt to Production: Build and Plug AI UI Into a Live App

Keren Fanan

In this session, I’ll explore how AI-powered tooling is transforming large-scale refactoring and codebase migrations, making these complex tasks faster and more efficient. By leveraging tools like Large Language Models (LLMs), static analysis, and refactoring frameworks, we can automate repetitive code transformations, accelerate migration paths, and reduce human error. I’ll share practical examples of how we can migrate legacy systems to modern frameworks, break monolithic architectures into service-based structures, and automate large-scale code changes across thousands of files. I’ll demonstrate how tools like OpenAI Codex, GitHub Copilot, and fine-tuned models for domain-specific transformations can assist in these processes, while still integrating with traditional migration tools and CI/CD systems. I’ll also cover the importance of developer oversight, highlighting lessons learned from real-world production rollouts and how to balance automation with manual reviews.By the end of the talk, I want attendees to walk away with a clear understanding of how to use AI to enhance their refactoring and migration workflows, ensuring they can handle large-scale transformations while maintaining code quality, consistency, and governance.

Refactoring & Migrations with AI: Smarter Code Transformation at Scale

Nikolay Gushchin

What if you let AI code alongside your devs—would it speed things up or slow them down? At Modus Create, we ran a 3-month internal experiment to find out. Two squads were tasked with building the same app: one squad had full access to AI coding agents like GitHub Copilot and Cursor, while the other worked with zero AI assistance. The results? Surprising, nuanced, and extremely relevant for any enterprise thinking about bringing AI tools into their software delivery process. In this session, we'll share productivity metrics, insights on code quality, cultural impact, and what we learned about pairing developers with AI. You'll walk away with a real-world perspective and a practical guide on how to scale AI-powered development across your engineering org—without the hype.

Vibe Coding at Enterprise Scale: What Happens When AI Joins Your Dev Team

Wesley Fuchter

Don’t get left behind—discover how AI is revolutionizing software engineering at the AI Coding Summit. Dive into cutting-edge talks and hands-on workshops on AI-powered software development. Network with industry leaders, explore game-changing tools, and stay ahead in the fast-evolving world of AI-driven development. Do not miss the biggest shift in software engineering.

AI Coding Summit

I'm attending AI Coding Summit with 5k other participants to learn how AI transforms software development and stay up to date with the latest AI tools - get your free remote ticket and join me there!

FocusReactive

Hygraph

FocusReactive is a <a href="https://focusreactive.com/nextjs-agency">NextJS agency</a> with deep expertise in <a href="https://focusreactive.com/headless-cms-agency">Headless CMS</a> and <a href="https://focusreactive.com/headless-commerce-agency">Headless Commerce</a>. We partner with Vercel, Shopify, Storyblok, and Sanity to build fast, scalable, SEO-friendly platforms - and provide NextJS tech &amp; AI SEO audits to optimize existing sites.