Beyond Passwords: Exploring Passwordless Authentication for Improved Security

With the increasing number of web apps, we can see more and more data breaches. Passwords are the biggest attack vector and are responsible for more than 80% of breaches, and they also lead to attacks such as:
* Credential stuffing
* Corporate account takeover (CATO)
* Password Spraying
* Brute force attack.
Let’s take a look at password alternatives - Passwordless Authentications.
We'll talk about various options and will see live examples of implementations.
And, of course, we will go over the benefits of using PasswordLess.

Passwords are the biggest attack vector and are responsible for more than 80% of breaches,
Let’s take a look at password alternatives, - PasswordLess Authentications.

Your agent failed. You blamed the model. You were wrong.

Every team does the same thing. Agent behaves weirdly in production - retries endlessly, drops tasks, returns confident nonsense. First reaction: swap the model, tweak the prompt.
It's never the model.
Multi-agent systems aren't an AI problem. They're a distributed systems problem with an AI layer on top. And most teams skip all the boring infra - state management, observability, failure handling, routing - and pay for it later.
We'll go through 8 agentic patterns (supervisor/worker, swarm, reflection, human-in-the-loop and more), and for each one: what the pattern does, where it breaks, and what infra you actually need before shipping it to production.

Gen-AI on Localhost: Prompt, MCP, Fine-Tune and RAG&Roll

Generative AI on your local machine?! In this hands-on workshop, we’ll guide you through the entire journey of setting up and optimizing Gen-AI models. You’ll start with prompt engineering, mastering prompts that deliver relevant results. Then, move on to fine-tuning techniques to tailor models for your specific needs. Discover Retrieval Augmented Generation (RAG), where document retrieval meets AI for smarter, context-aware answers. Get ready to RAG&Roll with Gen-AI on localhost! And of course, how could it be without it — we will create our own MCP server and use it right away!

Run Generative AI on your own machine! In this workshop, you’ll learn prompt engineering, fine-tuning, and RAG to build smarter, context-aware apps. And yes—we’ll even create and use our own MCP server. Get ready to RAG&Roll with Gen-AI on localhost

AI in Your Browser: Exploring Chrome's Built-In LLM

Let’s take a look at how Chrome’s built-in capabilities are shaping the future of web development. In this session, we’ll explore what’s possible with on-device and hybrid features, including tools for translation, summarization, and conversational interactions. We’ll walk through real-world examples, practical demos, and everyday use cases to show how these features can improve user experiences and make web apps feel smarter and more responsive. You’ll also learn how to integrate them into your own projects and get a sense of what’s coming next for modern web development.

Small LLM in your browser, huge UX improvements for your users. This talk explores Chrome’s built-in AI, showcasing translation, summarization, and chat APIs with real-world examples. Learn how to integrate these features into your projects to create smarter, more engaging web experiences.

Small LLM in your Browser, - Huge Opportunities for Web Applications

Let's see how AI is becoming a first-class citizen in your browser! In this session, I'll show you Chrome’s Built-In AI APIs - now available behind feature flags in regular Chrome and evolving in Canary. From language detection to summarization and even creative writing, these APIs promise to revolutionize how we build web applications.
Whether you're a developer, tech enthusiast, or decision-maker, this talk will equip you with insights and inspiration to stay ahead in the fast-moving AI landscape.

This session will dive into Chrome’s Built-In AI APIs, which are set to change the way we interact with and build web applications. Currently available behind feature flags in Chrome and advancing rapidly in Canary, these APIs offer powerful tools for developers to create smarter, more intuitive user experiences—all directly in the browser.

🔥 Generative UI: The Future of Frontend (And Why You Should Care)

Generative UI is already changing how we build frontends. We’re moving away from fixed, one-size-fits-all interfaces toward experiences that can adapt to users in real time. With tools like OpenAI’s App SDK, Google’s A2UI, and other emerging frameworks, UIs can now respond, adjust, and evolve based on context and user intent.

In this talk, we’ll look at what this shift means for frontend developers today. We’ll explore why modular approaches—such as Micro-Frontends, UI MCPs, and modern tooling—are becoming essential for building apps that work well with generative systems. You’ll learn the skills needed to design flexible, resilient interfaces, see practical examples of Generative UI in action, and understand how to use these technologies in a safe, realistic, and maintainable way.

Generative UI is here—the future of frontend where interfaces adapt in real time. This talk shows how AI-driven UIs, powered by modular designs like Micro-Frontends and UI MCP, can create apps that think, respond, and evolve with users.

(MCP Security) - How Your Friendly MCP Tool Might Betray You

We all love the convenience and power of AI-enhanced tools using MCP. But what if these handy servers had a hidden dark side? Let's dive into real-world examples of how MCP servers can silently leak your data, execute malicious commands, or even grant attackers access to your systems.
You’ll learn about sleeper attacks, tool poisoning, shadowing, and remote code execution—complete with chilling real-life cases and practical advice on defending yourself.
This is an eye-opening session that exposes why blind trust in MCP is a dangerous game.

AI-powered MCP tools make our lives easier—but they can also open the door to serious security risks. In this eye-opening session, we’ll uncover how attackers exploit MCP servers through data leaks, tool poisoning, sleeper attacks, and remote code execution.

From Idea to Production with AI: Build a Full-Stack App With VS Code & Copilot (or any other IDE)

In this hands-on workshop, we’ll take a bold app concept and build it together - from start to finish - using GitHub Copilot and an AI-ready IDE (like VS Code, JetBrains, Cursor, or others). You’ll see how AI can help you write a product plan, set up the database, build a backend with NestJS, and create a frontend with React.

No slides, no theory overload - just real development with real tools. We’ll use Copilot’s chat, agent mode, and IDE shortcuts to move fast, stay focused, and skip the boring stuff.

By the end, you’ll see that working with AI isn’t scary - it actually makes coding more fun. Let’s build something cool (and maybe blow your mind a little).

Turn an idea into a real app — fast. In this live workshop, we’ll use GitHub Copilot and an AI-powered IDE to plan, code, and ship a full-stack project with NestJS + React. No boring slides, just hands-on building with AI as your coding partner.

Goal: Build a full-stack app from scratch.

Format: 100% hands-on vibe coding, no heavy slides or theory.

Steps:
- Plan the project with AI.
- Set up backend (NestJS) with AI.
- Create and connect the database with AI.
- Build frontend (React) with AI.
- Add DevOps env with AI.
- Connect, test, and polish, guess what? - With AI.

Tools: Copilot chat, agent mode, IDE shortcuts.
Outcome: Participants leave with a working, deployeble app and practical AI-assisted dev skills.

Knowledge is the infrastructure. Everything else is just tooling.

Everyone's talking about being AI native. Management wants it. Developers are doing it. You've got Cursor, Claude, Copilot - the full stack.
And yet somehow, nothing actually got faster at the team level.
Here's the thing nobody warns you about: the problem isn't the AI. The problem is what the AI is working with. Your architecture is in Miro. Your PRD is in Confluence from 2022. Your README hasn't been touched in 14 months.
15 companies over 25 years. The one constant is that everyone has a knowledge problem. Everyone knows it. Nobody fixes it before buying the AI tools.
In this talk we'll go through what actually needs to happen first - how knowledge flows (or doesn't) across a product lifecycle, why RAG alone doesn't solve it, and why GraphRAG is the architecture that finally makes AI useful at the organizational level, not just the individual one.
We'll also look at what this looks like in production — real system, real stack, real lessons.

Every company has a knowledge problem. Everyone knows it. Nobody fixes it before buying the AI tools. This talk is about what happens when you do it the right way — from knowledge fragmentation across your product lifecycle, through RAG and its limits, to GraphRAG in production. Real system, real stack, real lessons.

Big Model vs Big Harness: The Debate That's Actually Shaping AI Products

Every few months a new model drops and the room gets loud again. This is the one. Agents will change everything. Then we go back to our desks and the agent forgets what it was doing, loops on a broken test, or ships the wrong thing at 2am.
We kept blaming the model. It wasn't the model.
The real fight was one layer down — in the harness. The loop, the memory, the tools, the guardrails. The thing that turns a text generator into something that finishes a task.
This talk is from the trenches. What broke first. What we over-built and ripped out. When "the model is dumb" was a harness problem in disguise — and when it was the opposite, a cage the model had outgrown.
Just what we saw, what we got wrong, and the mental model we wish we'd had on day one. For devs, PMs, anyone shipping AI features.

Micro-Frontend Architecture and Module Federation: Making the Right Choices for Your Project

The micro-frontend architecture is attracting more and more developers, and module federation is a great addition to this architectural pattern. And as with any new technology, new questions are raised.
Let's take real-life examples and live coding to answer the following but not limited to: how we should divide apps and whether there are specific criteria to separate them. Is my project suitable for the Micro-Frontend at all? When should I use Micro-Frontend and when Module Federation? And some other questions.

This talk is designed to provide practical, real-life examples and live coding demonstrations that will help attendees navigate the world of micro-frontends and module federation more confidently. The presentation will answer essential questions, such as when to use micro-frontend, when to use module federation, and how to determine if a project is suitable for these approaches.

Thank you for hiring me, but I'm quit! 12 companies in 12 years and 12 lessons Learned.

I want to share an exciting 12-year journey through the tech world, moving through 12 different companies. Learn how to confidently make job changes, respect your needs, ace interviews, get better job offers, and gain lots of tech experience.
This talk is great for anyone thinking about changing jobs or wanting to grow in their career. Find out how saying, "Thank you for hiring me, but I’m quitting," can actually be a good step for finding success and learning more about yourself.

This talk is perfect for anyone working in tech. Whether you're thinking about changing your job for the first time, want to improve your job selection, or hope to learn more tech skills, this is for you.
This is the first time this talk is being given.