Georgios Diamantopoulos

Georgios Diamantopoulos

Georgios has spent 16 years building software in startup environments, always the one responsible for making the technology work — and always cleaning up what happens when speed beats judgment. In 2019 he co-founded Zero to MVP, where his team has shipped over 25 products that can pivot and scale. Lately, a new kind of project keeps landing on his desk: vibe-coded products that look great, work on the surface, and are quietly falling apart underneath. He's been untangling AI-generated codebases and figuring out what constraints would have prevented the mess in the first place. He speaks internationally about pragmatic engineering, developer health, and what happens when we hand powerful tools to people without guardrails.
Vibes Don't Scale
AI Coding Summit BerlinAI Coding Summit Berlin
Upcoming
Vibes Don't Scale
A founder spent six weeks with AI tools and shipped 300,000 lines: a WhatsApp clone with real users and a polished UI. Underneath, security holes, queries that pull an entire table to count its rows, and a codebase three senior engineers couldn't untangle. With low-code the limit was visible: the blocks ran out and you called an engineer. Vibe coding has no visible wall. Nothing stops you, nothing warns you, until production. He never saw the line he crossed.

The constraints didn't vanish, they shifted: security, maintainability, performance, UX. The AI generated with a weak feedback loop: generate, glance, ship. Exploration is real value: you have to build things to understand what you're building, and AI makes that faster than ever. So I'll rebuild it the other way: hand the AI the instruments engineers spent years mastering, as a tight loop it answers to while it writes. Constraining AI before it writes, not after, is what I call Human-Driven Development.

Tooling only goes so far: it raises the floor and can't make the judgement call. The hard skill is catching the moment a prototype gets run as a product, bearing load it was never designed for, and humble enough to get a real review first. Drawing that line is what separates a product from a rewrite.

I'll run both loops on the same work, generation after generation, and you'll watch them diverge, my AI sidekick Loyal calling out what's rotting, or holding, underneath. AI made the engineer the last line of defense.
Build the Harness: Guardrails That Make Agent-Written Code Safe to Merge
AI Coding Summit BerlinAI Coding Summit Berlin
Nov 26, 15:00
Build the Harness: Guardrails That Make Agent-Written Code Safe to Merge
Workshop
A founder spent around eight weeks of his spare time adding 349,000 AI-written lines to a sports platform we had built. On the surface it worked. Underneath, anyone signed in could read strangers' private chats, and the tests that came with it passed. Three of us could not review our way through it.

Agents write faster than any team reviews, and an AI marking its own homework gives itself a pass. The harness is the scaffolding in your repository that an agent works inside, so every session inherits your standards and every change meets checks the model doesn't control. In three hours you build three of its five layers:

Repository instructions every agent session picks up, whichever tool it runs in
Deterministic enforcement: your team's rules as custom checks that fail the build (analyzers, lint rules, strict types, post-edit and pre-commit hooks, CI that blocks the merge), with error messages the agent has to fix before it continues
A validation loop the model doesn't grade: tests written from the spec by a session that never saw the code, and a check that calls every endpoint as every kind of user
You work on a deliberately vibe-coded club app, then spend the last half hour on your own repository. Every merge faces one test: could you debug it half asleep at three in the morning? If not, it doesn't merge.

What participants take away

- Structure a repository so any coding agent inherits your standards
- Move enforcement into deterministic tooling that gives agents immediate, non-negotiable feedback
- Validate agent work with checks the model doesn't grade: tests from the spec, and every endpoint called as every kind of user
- Hold your next merge to a gate you can defend at three in the morning
Practical exercises

1. Run the task with no harness, find the defects in your own run, and see that the agent's tests pass
2. Write house rules as repository instructions and re-run a probe task
3. Write a custom lint rule (ESLint in the lab; a Roslyn analyzer or your stack's equivalent at home) that fails the build when code changes a balance outside the ledger, with an error message written for the model; wire it to a post-edit hook and watch the agent fix its own code
4. Break the hook on purpose and watch the edit go through: hooks fail open
5. Have a second session that never saw the code write tests from the spec, and run a check that calls every endpoint as every kind of user; it finds the hole the agent added and one nobody touched
6. In your own repository: your team's most repeated review comment as a custom lint rule or analyzer that fails the build, or one spec-first test for code nobody fully owns

Prerequisites

A laptop with Claude Code, Codex or a comparable coding agent installed and authenticated, and the lab repository cloned before the session; we'll send a setup check in advance. Bring a repository you actually work in for the last half hour.
Register
Shifting the Trajectory: Undoing the Damage of Working in Front of a Computer Screen
React Advanced 2025React Advanced 2025
21 min
Shifting the Trajectory: Undoing the Damage of Working in Front of a Computer Screen
We're an industry that solves impossible technical challenges, builds systems serving billions, and automates the world - yet we haven't figured out how to sit at a desk without destroying our bodies. I learned this the hard way: active engineer → COVID couch potato → 41-year-old developer with chronic pain. The research reveals I was just one predictable data point in a massive pattern.This isn't about being "out of shape." Within hours of sitting, arteries lose elasticity and blood pressure spikes. After one day, insulin dysfunction kicks in. Within days, 4,500+ genes rewire themselves and fat-burning enzymes shut down by 90%. Structural adaptations create "tech neck," and spinal damage now appears in children as young as 9. We're systematically breaking our bodies while building the digital world.Here's what shocked me most: exercise can't save us. You can't out-train 8 hours of sitting damage. The solution isn't better ergonomics - it's a complete mental reframe of how we work and live as developers. I'll share the latest research and specific strategies that can shift your trajectory from inevitable decline to sustainable vitality. Because the alternative isn't just pain - it's a future where we can't move freely through life at all.