Schedule

Vibe coding feels productive until you have to maintain it. Behind the agent "thinking..." you ignore and the code you never opened lies a growing pile of wasted tokens, nondeterministic behavior, and compounding errors hiding in plain sight.This talk pushes back on the status quo: elaborate agent architectures, "prompting astrology", overnight automation loops burning through context windows and credit cards. We'll look at why determinism, state machines, and explicit guardrails aren't "old-school"... they're the only sustainable way forward.We'll look at why vibe coding compounds technical debt faster than any era before it, and how modeling behavior explicitly lets you ship AI features you actually understand, maintain, and trust.

The engineers who make it to staff level aren't the ones who wrote the cleverest code. They're the ones who figured out that code was never the point.Most of us learn this too late — after burning hours on solutions no one asked for, defending implementations no one remembers, wondering why technical excellence isn't translating into career growth.Agentic AI just made this lesson impossible to ignore. But for engineers feeling anxious about that, there's good news: what actually drives growth at every level — senior, staff, and beyond — has always been more human than technical. How you communicate.

We had more incoming requirements than our team could review, so we built a multi-agent pipeline in CI that takes raw requirements and turns them into reviewed, scored, spec-ready work items. Each requirement gets scored across five dimensions with a hard pass threshold. The ones that pass go through four parallel AI reviewers covering Feasibility, Testability, Scope, and Architecture. Each reviewer writes its findings back to Jira as markdown that engineers actually pick up and use.

A test that passes for the wrong reason is the worst failure in test code: it certifies a broken GPU driver and nothing alarms. I maintain the Khronos Vulkan Conformance Test Suite and run AI coding agents on it every day. This talk is the grading discipline that keeps that work honest: every agent result checked against a human-reviewed reference, so I can tell a correct fix from a lucky-looking one before it ships.

Every repo has them now: CLAUDE.md, AGENTS.md, a folder of markdown rule files written to steer the AI. Write the rule once, get the code you want. Except these files are advisory, not enforced, as every major vendor says so in their own docs. The research backs it up.

I built a software factory: a Kanban board where dragging a card starts an agent, tasks that unblock each other as they finish, agents with their own roles and prompts, and an adversarial reviewer that goes through the code before I ever see it. It worked. I barely used it.The problem wasn't the factory, it was that I kept working the way I always had: sitting with an agent, pushing it forward, jumping to the next one, course correcting. Everything interactive.

AI has made writing code cheaper, but the hardware doesn’t get any cheaper.I build React apps used worldwide, many running inside WebViews on affordable Android phones. These devices often represent the slowest 10% of user experiences. Even when all CI checks pass, performance issues can still slip through review.AI has also made another part of this process harder. We can release more code, but reviewers still have the same time.

Application modernization has always been hard. The hardest cases combine decades of complexity with missing knowledge, proprietary technology, hardware dependencies, unclear requirements, and systems that cannot simply be switched off. Agentic AI gives us a new chance to make these projects technically and economically viable. It can reconstruct knowledge, explore unfamiliar systems, and support modernization at a previously unrealistic scale.

Shipping a new feature is easy. Knowing if it actually improved anything? That's the hard part.In production React applications, small UI changes can have a big impact on user behaviour. A new form, validation change, onboarding step, checkout flow, or performance improvement might reduce friction - or quietly make the experience worse.Many teams still ship these changes based on intuition rather than evidence.

React has changed a lot in the last year: React 19, 19.1 and now 19.2 brought a stable React Compiler, new hooks like useEffectEvent, the <Activity /> API, and better SSR primitives such as Partial Pre rendering. And more.In this talk we’ll take a demo React app that’s full of effects, memoization and “old school” patterns, and modernize it step by step.

Asking an AI to refactor 200 files across your React codebase burns tokens, takes minutes, and sometimes hallucinates. A codemod can do the job reliably (and for free). But if you're not familiar with writing codemods, that's a big step to climb. In this talk, you'll learn how to use AI to craft the codemods your team needs.

React is no longer just for web applications. Some of today’s prominent AI developer tools, including Claude Code, Gemini CLI, and GitHub Copilot CLI, bring React into a rather different environment: the terminal. At the center of this development is Ink, a React renderer for building interactive command-line interfaces using components, hooks, and Flexbox-like layouts.But the bigger shift is not just from browser to terminal. AI applications are moving from sim- ple chat interfaces toward harnesses: systems that connect models with tools, context, workflows, and humans.

A couple of weeks after shipping our part of a monolith React application, we learned it now needed to run in the Grammarly for Chrome browser extension—and fast. Dive with us into a story about what to expect from such a transition, the intricacies of cross-context communication, and the pitfalls of the extension lifecycle. Will the architecture, the design patterns, and a reactive approach save the day once again, or was the project doomed from the inception?

Zattoo has shipped streaming apps for over two decades, adding platforms one by one: Web in React, Android in Kotlin, Apple in Swift. Every new platform multiplied the work instead of extending it. The same feature built three times, in three stacks, by three siloed teams.Then Amazon invited us to build for Vega, their new Linux-based OS where React Native is the primary UI framework, not an add-on. That became our catalyst to rethink everything: one React Native codebase across Web, Android TV, Apple TV, and Vega, held together by build-time overrides instead of runtime branches, organized by product domain instead of by platform.This is the honest story of that migration.