Stages, slides, stories from the room.

Most engineers are using AI the wrong way. They paste code into a chat, accept whatever comes back, and ship it. That works fine, right up until it doesn't. The AI makes things up, the code ends up doing something different from what was asked, and nobody can figure out why.

I've been on both sides of this. This talk is about what actually changes when you stop treating AI as a magic box and start treating it like any other tool that needs decent inputs to produce decent outputs. That means giving the agent enough context to not guess, writing a short spec before you start so there's something to check the result against, and not skipping the review just because a machine wrote the code.

It sounds obvious when I say it like that. The gap is in doing it consistently, and that's what we'll work through: we'll analyze how spec-driven development, context engineering and verification mechanisms allow us to produce production-quality code with AI.

Vibe coding feels great when working on a greenfield weekend side project alone, but it falls short when working with complex real-world systems. As AI coding assistants become more capable, we're discovering that good engineering discipline matters more than ever.

That's why new methodologies of AI-assisted development are emerging. The spec-driven approach is not shiny, it has a learning curve and forces you to think, reason, and requires deliberate collaboration between human and machine.

This approach brings proven engineering practices in the SDLC to write systems which don't explode in production. It's not fun, but it's the evolution we need to work with AI agents at scale in a mature industry.

Give an AI access to a real Node.js runtime, and things start to get interesting. It can run code, install packages, generate files, and even launch servers on the fly. In this talk, you will see how I built a Node.js Sandbox server powered by the Model Context Protocol (MCP), an open standard that connects AI to real tools and data in a safe, controlled way.

We will walk through how the sandbox works: starting fresh Docker containers, installing npm packages on the fly, executing JavaScript, and sending back logs or files. Everything happens through simple MCP messages, allowing the AI to interact with your system just like a developer would, only faster.

You will see how this unlocks powerful use cases like generating charts with Chart.js, summarizing long articles from the web, creating and testing QR codes, scraping and saving content, generating PDFs and fake CSV data, or even spinning up mock APIs in seconds. By the end, you will know how to build your own MCP server and give your AI the keys to a real coding playground.

Remember Node.js in 2020? It worked, but you needed countless dependencies to get anything done. Fast forward to 2026 and Node has completely transformed. It's faster, more capable, and packed with modern features that make it feel like a brand-new runtime.

Imagine going through every changelog from the past six years and condensing it all into one talk. From the native test runner and permission model to built-in TypeScript support and beyond, we'll explore everything you can now do out of the box. Stop writing Node.js like it's 2020 and discover what the modern runtime can truly achieve today.

In today's world, repetitive tasks can be automated to make life easier. I'll guide you in building a custom Workflow Engine using TypeScript to simplify your daily routines. We'll explore practical uses and create various plugins, including connections with IoT devices and Large Language Models.

You will learn how to build a Workflow Engine that uses Directed Acyclic Graphs (DAGs), allowing for complex workflows with parallel tasks and decision-making paths. We'll explain how graph structures support automation, using algorithms like Depth-First Search for validation. You'll also learn to use recursive Promise chaining to handle tasks running at the same time and branching paths, ensuring workflows run smoothly.

We'll begin with the basics of workflow automation, then move to real-world examples that combine software, hardware, and AI. The goal of this talk is to give you a blend of useful theoretical foundations and practical tools to quickly build automations using JavaScript or TypeScript.

As cherry on the cake, we will look at how to build a dynamic plugin system to build your plugins and expand the capabilities of the base engine.

I bet you've always used React to build websites and applications, right? What if I told you that we can also edit a movie with it! Learn how a simple render engine built in React and Node.js works to make videos using React components.

Also, you will learn how to create a scalable render-farm using AWS. The main library to build the render engine is Remotion and allows to render videos programmatically.

During the talk we will create a video together and we will render it in a few seconds in cloud!

Backend developers regularly face the challenge of implementing secure authentication and authorization. While solutions like Auth0 and Keycloak are popular, new open-source projects like Logto are emerging as strong contenders.

In this session, we'll demonstrate how to secure your backend using OAuth 2.0, highlighting the unique features that make Logto an excellent choice for your authorization needs. We'll also cover how to easily deploy Logto in the cloud using Docker, enabling you to enhance your security infrastructure with minimal effort.

In this talk, we'll look at what it takes to move from being a Senior Engineer to a Tech Lead. We'll start by exploring the Senior Engineer role, covering what's expected and which technical and personal skills are needed to do well. Then, we'll meet Bob, a Senior Engineer who wants to become a Tech Lead but feels like it's a big leap.

We'll then talk about what a Tech Lead does, the skills they need, and how they help their team. I'll share practical ways to start building these skills, including live examples of key soft skills through interactive, scenario-based exercises. I'll invite audience members to join me in these real-world situations, where we'll role-play and have a dialogue to show how a Tech Lead responds in different scenarios.

At the end, I will provide a detailed step-by-step roadmap to help you move from Senior Engineer to Tech Lead. This talk will leave you with clear steps and motivation to take your career to the next level.

Engineer or Manager: who wears the cooler tech cape? Dive into the great debate with insights from 'The Manager's Path' and 'The Staff Engineer's Path'. From code-wrangling wizards to tech team captains, get a fun peek into the world of tech's top jobs. Pick your path or just enjoy the ride!