Prompt-Driven Development: Aligning Ideas, Tests and Code en

What if building software didn’t start with code? You’ve got your product docs, user stories, and mocks—all the ideas laid out. But when it’s time to build, what if the next step wasn’t writing code but writing prompts instead?

Imagine this: prompts that describe what the product should do, in plain language everyone on the team can understand. Those prompts turn into tests, and once the tests look right, the AI writes the code to make them pass. Suddenly, everyone—product managers, designers, developers—is on the same page, shaping the product together.

Maybe this is how TDD finally makes sense—not just for developers but for the whole team. Tests are a shared source of truth, driven by prompts, keeping the focus on what we’re building—not just how.

But can prompts really capture intent? What about the AI’s “black-box” code—how do we trust it? And does this shift make building software feel more collaborative—or just different?

In this talk, we’ll explore these ideas, what might work, and what might break along the way. What if building software from prompt to test to code is exactly what we’ve been missing?

RoboCoders: Judgment Day – AI IDEs Face Off en

Can AI-powered IDEs take software development to the next level? Unlike traditional code assistants that provide suggestions or guidance, AI-driven IDEs like Cursor and Windsurf promise to act as full-fledged agents capable of handling entire workflows. In this live showdown, we’re putting that promise to the test by challenging these tools to build a smart light bulb controller—something we’ve never developed before.

From setting up the project and implementing features to testing, debugging, and optimizing, the AI will take the reins. This isn’t about helping—it’s about doing. The audience will decide the winner based on how well the tools perform and, of course, whether the demo actually works.

Join us to see if AI IDEs can deliver on their bold promise of transforming development, or if they’re just another stepping stone on the path to something bigger.

This is a fun hands–on talk – two speakers, two laptops, two IDEs, one demo. Who will do better? Whose demo will even work? Who will have a better developer experience? The audience will be the judge.

Codepocalypse Now: LangChain4j vs. Spring AI en

Which Java framework handles AI better: LangChain4j or Spring AI? In this live coding showdown, we’ll build a semantic code search application from scratch, putting both frameworks to the test. We’ll cover project setup, using language models, setting up a retrieval-augmented generation workflow, and creating a REST API.

You’ll see how these frameworks handle embedding generation, vector database integration, and real-world development challenges. By the end, the audience decides who wins—based on which framework gets the job done faster, better, and with less hassle (and whether the demo actually works).

This isn’t just a comparison; it’s a live experiment under pressure. Come and see which one comes out on top!

This is a fun hands–on talk – two speakers, two laptops, two frameworks, one demo. Who will do better? Whose demo will even work? Who will have a better developer experience? The audience will be the judge.

Technical Enshittification: Why Everything in IT is Horrible Right Now and How to Fix It en

Software is a mess. Everything feels bloated and sluggish. Bugs pile up. Updates break more than they fix. Even basic apps demand absurd amounts of computing power. And innovation? If you count shuffling UI elements or slapping a ChatGPT button onto everything, sure.

The problem isn’t bad engineers. It’s that building software has turned into an obstacle course. Every step—writing, reviewing, deploying—is buried under layers of tools, approvals, and abstractions. A simple change takes weeks. We spend more time wrangling complexity than shipping code. No wonder quality is tanking, and real progress feels nonexistent.

So how did we get here? More importantly, how do we stop making it worse? Fixing the Googles and Metas of the world might be out of reach, but your projects don’t have to follow the same path. This talk is about cutting through the mess—how AI, smart tooling, and better developer workflows can actually help instead of adding more noise. Let’s figure out how to build good software again.

Coding Fast and Slow: Applying Kahneman's Insights to Improve Development Practices and Efficiency en

How does behavioral psychology connect to coding? This talk explores how understanding and managing your mental energy can transform the way you work. Using accessible research, including Daniel Kahneman’s concepts of “fast” and “slow” thinking, we’ll dive into how different types of thinking impact decision-making and productivity. We’ll also discuss how to conserve mental fuel, so you have the focus and clarity needed for critical tasks—even at the end of a demanding day.

In addition to understanding how our minds work, we’ll talk about practical techniques for managing time and allocating mental resources effectively. This includes strategies to reduce context switching, avoid wasting mental energy on low-priority tasks, and stay focused on what really matters. By using your mental energy wisely, you’ll be able to maintain productivity and avoid burnout.

If you’re interested in learning how to apply behavioral psychology to your workflow, improve time management, and make smarter decisions with less effort, this talk is for you.

DevOps for developers (or maybe against them?!) en ru

"DevOps" is the operations people’s crafty plan to make developers do other people's work, but we are smart enough to see right through this naive rebranding trick!

Baruch suggests you think about it: we, the developers, have written all the code. It passes all the tests; it obviously works, and works well (Are we a little proud? We are!); so we are DONE.

Now, out of the blue, a bunch of "thought leaders" (all with an operations background, mind you!) are trying to tell us that we have to learn YAML, Docker, Kubernetes and Terraform to deploy our software because suddenly it is our concern?!

In this talk, we'll discuss why developers do or don’t need DevOps. We'll consider arguments made by DevOps visionaries and see whether they hold water. Hopefully, by the end of the talk, we'll understand whether DevOps really helps developers to deploy better code to production more often, or if it is just another scam made up by marketing and evangelists.

This is a fun and provocative talk. I am starting by claiming that developers have no incentives to do any DevOps and will work my way to explain why; although there is some truth in that, it doesn't matter. The business must commit to DevOps, and once the business is committed, everyone has to be on board.

DevOps для разработчиков (или против них?!) en ru

DevOps — это заговор сисадминов, чтобы заставить разработчиков делать чужую работу, но мы слишком умны, чтобы попасться на эту элементарную уловку ребрендингом! Посудите сами: мы написали код, он проходит тесты. Он, очевидно, работает и работает хорошо (Мы гордимся собой? Да!). И тут мы закончили.

Но приходят эти «визионеры» (все из operations, прошу заметить!) и рассказывают нам, что теперь надо учить YAML, Docker, Kubernetes и Terraform, потому что внезапно это наша головная боль?!

В этом докладе мы поговорим о том, зачем разработчикам нужен или не нужен DevOps. Мы рассмотрим аргументы, которые приводят идеологи DevOps, и решим, состоятельны они или нет. К концу доклада, будем надеяться, нам станет понятно, действительно ли это способ, который поможет нам (разработчикам) поставлять лучший код в прод чаще, или это, как всегда, разводка маркетологов и евангелистов.

Can We Trust Al-Generated Code? Maybe We've Been Asking the Wrong Question. en

No one trusts AI-generated code. It looks right. It sounds confident. But does it actually do what we expect?

Having AI test its own work doesn’t help. If we can’t trust it to write code, why would we trust it to write tests after the fact? That’s not verification; it’s an echo chamber.

That leaves us manually checking everything. The safest bet is to assume it’s wrong and review every line yourself, which doesn’t exactly scream “productivity boost.”

So what’s the alternative?

Maybe we’ve been looking at this the wrong way. AI might be trustworthy, but only if we rethink how we guide it. What if there were a way to ensure it understands intent before it writes a single line of code? A way to catch mistakes before they happen instead of fixing them afterward?

An excited AI developer advocate and a cynical senior engineering manager take the stage to debate whether AI-driven development is finally ready for prime time or just another way to get things wrong.