Applying AI Events in Wrocław

[Event in English 🇬🇧]
Welcome to the third Claude Community Wrocław meetup - a community-driven initiative built by builders, for builders https://claudecommunity.pl/

We share real stories of how we use Claude, Claude Code, and Claude Cowork in our daily work. No product pitches, no vendor talk - just honest experience from people who build with these tools every day.

This event is NOT affiliated with Anthropic. This is an independent community initiative.

Pizza and drinks are included and the event is free, sponsored by CSHARK
If you wish to speak at our future events, use this form: https://forms.gle/8fRNxrCG8JWJUkRQ9

🟢 Where and when?
Concordia Design Wrocław (CSHARK office), wyspa Słodowa 7, 50-266 Wrocław
6PM CEST 🔴 the location is different than usual 🔴

Agenda
➡️ 18:00 - Welcome & intro by Claude Community Wrocław organizers
🧑‍💻 18:05 - Trust, but eval: from one skill to a team of agents and proving each step actually works - Konrad Dżbik
🧑‍💻 18:45 - What’s the actual ROI of AI in your SDLC? Measuring it with the metrics we already have - Maks Piechota
🍻 19:25 - Networking & Pizza
🧑‍💻 19:55 - Lowering the Floor, Not the Ceiling: Bringing Non-Technical Users into Agentic AI - based on real example - Marcin Krok

➡️ Trust, but eval: from one skill to a team of agents - and proving each step actually works

Everyone ships skills, plugins and multi-agent setups for Claude Code. Almost nobody can prove they help – or say what they cost. I'll walk up the autonomy ladder with real artefacts from a 200-person software house and show how the same discipline – a baseline, a grader and a budget – applies at every rung.

🎤 Konrad Dżbik - I'm Head of AI at CSHARK, a software house in Wrocław, where I built the AI Vertical from a blank page and brought Claude into everyday work across the whole company. I run Open mAIc, a workshop series that gets developers, testers, PMs, marketing, and finance learning in the same room, and I keep teams supplied with skills and plugins through our in-house CShark-Hub marketplace. I started out writing C#/.NET, hold a Google Cloud Professional Cloud Architect certification, and I'm a certified Bielik trainer with a soft spot for Poland's sovereign LLM scene. My natural habitat is Claude Code, agentic systems, MCP, and multi-agent orchestration — and my firm belief is that an agent you haven't evaluated is just a very confident guess.

➡️ What’s the actual ROI of AI in your SDLC? Measuring it with the metrics we already have

A lot has already gone into AI tools: licences, tooling and a good deal of your teams’ time. So what’s the return? There’s no clean formula for it yet, but measuring delivery performance isn’t a new problem. My thesis is that AI in the SDLC is one brick, not a new building. What you’re after is still engineering performance, so the metric set stays broadly the one we already had, with some tactical extensions for what’s genuinely specific to agents. We’ll look at the data your AI vendor is already collecting on your behalf, DORA and what its authors say about measuring AI-assisted delivery, DX Core 4 and its tension metrics read against each other so no single number can be gamed on its own, The Product Operating Model, and the product metrics that turn faster delivery into something the business can read.

🎤 Maks Piechota - I’m a Senior Engineer on the AI Platform team at FirstConnect Insurance Services. My whole career, from enterprise (Dolby Laboratories) to US startups, has centered on one thing: making software delivery faster without giving up quality, through demanding Engineering Excellence practices (TDD, BDD, Extreme Programming, Trunk Based Development, Continuous Delivery) backed by hands-on software architecture. As Head of Engineering at Bridge I went deep into DORA and DX, and that became the baseline I brought to leading AI adoption into the SDLC at an American insurtech. I believe the practices the industry spent decades building to minimize human-error risk are exactly what AI-generated code needs, and I share what I learn at meetups and conferences.

➡️ Lowering the Floor, Not the Ceiling: Bringing Non-Technical Users into Agentic AI — based on real example

Agentic AI keeps raising its ceiling while the floor to get in stays high — install a toolchain, live in a terminal, wire up credentials. Through a real product built on Claude Code — one-button dependency install, shared knowledge bases, agents in isolated git worktrees under budget caps and merge review — and real onboarding stories, I'll show where the floor actually sits for non-technical users and the engineering it takes to lower it without dumbing anything down. The last mile of AI adoption is rarely the model — it's the setup screen, and it's ours to fix.

🎤 Marcin Krok - I'm an AI enthusiast and co-founder of CSHARK, a Wrocław-based software house I've been building since 2014. A former software developer with 25 years of experience in IT — including 15 years running multiple businesses in the software space — I spend a lot of my time these days wrestling with what it actually takes to get AI working inside a real engineering org, not just in a demo. That's also what's behind the examples I'll be sharing at this talk: real onboarding stories from a Claude Code-based tool built to get non-technical teams past the setup screen and actually shipping with AI agents.

Sponsor

CSHARK (https://www.cshark.com/)

Join us on October 29th for an exciting evening packed with deep technical insights into the world of Artificial Intelligence and Cloud computing! Whether you are interested in building sophisticated AI agents in the cloud or exploring the power of local LLMs for personal knowledge management, this event has something for you.

Come for the knowledge, stay for the pizza and great conversations with fellow tech enthusiasts! 🍕🗣️

🗓️ Agenda

18:00 – Welcome & Intro 👋

18:15 – Presentation 1: Agents Development in GCP (Remigiusz Marciniak) ☁️

19:00 – Pizza & Networking Break 🍕🥤

19:30 – Presentation 2: Personal Mind Trainer: How to Build a Local Mentor with Gemma and Gemini (Adrian Romański) 🧠

20:30 – Event Wrap-up & Closing 🎬

🎤 Session Details
1️⃣ Agents Development in GCP By Remigiusz Marciniak

This session provides a comprehensive introduction to Agent Development within the Google Cloud Platform (GCP), covering the key stages of building AI agents from scratch. If you want to understand the end-to-end lifecycle of building AI agents in the Google Cloud ecosystem, this talk is for you!

Key takeaways include:

Spec-Driven-Development: How to properly define agent behavior and requirements.

Developing & Deploying: Best practices for bringing your agents to life on GCP.

Enhancing with Memory: Adding context and state to make your agents smarter.

Evaluating Agents: Methods for testing and assessing agent performance.

2️⃣ Personal Mind Trainer: How to Build a Local Mentor with Gemma and Gemini to Test Your Knowledge By Adrian Romański

Most AI note-taking tools boil down to a simple chat with your documents. This model gives a false sense of mastery and frees us from deep thinking—when AI instantly serves ready-made answers, the deep learning process disappears. But what if we reversed this relationship? What if you could transform your knowledge base into a demanding trainer, with a full guarantee of privacy and offline independence?

In this 45-minute technical session, we will explore how to build a personal cognitive mentor using a unique two-tier architecture that doesn't send a single private file to the cloud and works even without internet access:

💻 Local Gemma (The Personal Trainer): Runs directly on your laptop and raw notes. While you're traveling on a train or plane, it takes on the role of a coach: leading a Socratic dialogue, challenging you, and forcing you to explain concepts in your own words (the Feynman technique).

☁️ Cloud Gemini (The External Judge): Steps in when network access is available, acting in an LLM-as-a-Judge pattern. It never sees your private database—only the content of the generated question and your answer. It strictly catches logical errors, exposes superficial knowledge, and acts as a demanding, uncompromising auditor.

RSVP now to secure your spot! We can't wait to see you there! ✨

Agenda

---

Speakers

Remigiusz Marciniak - Capgemini (Senior Software Engineer)

Remigiusz Marciniak is a Senior Software Engineer at Capgemini with over 5 years of experience in software development. He joined Capgemini in December 2025, after previously working at Nokia.
Remigiusz holds three Google Cloud certifications: Associate Cloud Engineer, Professional Cloud Architect, and Gemini Enterprise Agent Development.Passionate about innovation and continuous …

Adrian Romański - Push-Based (Full Stack Developer)

Moja przygoda z programowaniem zaczęła się od C++ w liceum. Tak bardzo mi się spodobało, że zacząłem studia na PJATK, gdzie specjalizowałem się w robotyce. Jednak po zdobyciu pierwszych doświadczeń zawodowych zorientowałem się, że to nie do końca moja droga. Zdecydowałem się zmienić kierunek na web development, zaczynając jako Java developer pracujący z frameworkiem Spring.
Na początku f…

Hosted By

Luka Malakhau, Software Developer

Karol Wrótniak, GDG Organizer

Artur Skrzypczyk, Organizer

Jan Łuczka, Android Developer

Szymon Mazanik, Flutter Lead

Adrian Romański, Organizer

I’m a Full Stack Developer working primarily with Java and Angular, with a strong focus on modern frontend development.
Over the past years, Angular has become my main area of specialization, both in day-to-day work and continuous self-development.

I’m particularly interested in:

• Angular architecture, performance, and component design
• State management using RxAngular and NgRx
• Nx-based monorepo architectures for scalable applications
• Web Accessibility (a11y)
• Developer Experience and tooling
• AI-powered solutions supporting frontend and developer productivity

Lately, I’ve been diving deeper into accessibility, focusing on semantic HTML, WCAG guidelines, and building inclusive, accessible Angular components.

Dawid Perdek, Organizer

Software Developer with a decade of experience in various technologies, company sizes and industries. Focus mostly on frontend. Curious of how products are making money, loves good food and good people.

---

Gold

Capgemini (https://www.capgemini.com)
Capgemini is an AI-powered global business and technology transformation partner, delivering tangible business value. We imagine the future of organizations and make it real with AI, technology and people. With our strong heritage of nearly 60 years, we are a responsible and diverse group of 420,000 team members in more than 50 countries. We deliver end-to-end services and solutions with our deep industry expertise and strong partner ecosystem, leveraging our capabilities across strategy, technology, design, engineering and business operations. The Group reported 2025 global revenues of €22.5 billion.

Complete your event RSVP here: https://gdg.community.dev/events/details/google-gdg-wroclaw-presents-ai-amp-cloud-stream-meetup/.

Hej Społeczności!

W tym miesiącu temat, który dotyczy niemal każdego czyli AI w rekrutacji w Techu/IT. No bo kto nie był lub nie będzie rekrutowany?

Nasi stali bywalcy już wiedzą, że miejsce staramy się dobrać właściwie do tematu, więc Ekonomiczny w temacie HR to właściwy wybór:)

WAŻNE!: Pizzę, napoje i broszury (kolejny raz) stawia życzliwym nam sercem i kieszenią Billennium - zrobią też quiz z nagrodami!

Jeżeli myślisz, że temat tego Meetupu może kogoś z Twoich znajomych zainteresować - bierz ich ze sobą! Szczególnie tych, którzy pracują w obszarze HR lub HR-Tech!

-------------------------------------------------------------------------------------------------
Agenda:

• 18:00 <- Powitanie.
• 18:05-18:15: Słowo od Partnera
• 18:15 - 19:00 Krystian Kozieł: "Next-Gen Tech Screening"
• 19:00 - 19:15 --------- PRZERWA ------------
• 19:15 - 20:00 Bartek Kolasa, : "It’s a match! AI, rekrutacja i czemu to nie jest takie proste"
• 20:00 - 20:15 Ankieta Ewaluacyjna i plany WAIT
• 20:15 - 21:00 --- PIZZA TIME + Networking ------

--------------------------------------------------------------------------------------------------
Prelegenci:

Krystian Kozieł, (LinkedIn):

Krystian jest doświadczonym inżynierem i praktykiem z wieloletnim stażem w dziedzinie AI i Machine Learning. Na co dzień zajmuje się projektowaniem oraz budową platform służących do optymalizacji procesów sztucznej inteligencji. W swojej pracy skupia się na architekturze, wydajności i skalowaniu rozwiązań, pomagając przekuwać teoretyczne rozważania w działające systemy.

Bartek Kolasa (LinkedIn)

Bartek jest z wykształcenia matematykiem i robotykiem, które swoje życie zawodowe związał z polskimi startupami. Był founding engineerem w polskim Palantirze czyli spółce DataWalk a obecnie rozwija jako Chief Technical Officer polska platformę rekrutacyjną TechTree współpracując z najważniejszymi markami polskiego new techu jak Eleven Labs, Viktor czy Pocket.

--------------------------------------------------------------------------------------------------
Abstrakty:

Krysitan Kozieł:
"Next-Gen Tech Screening"

Współczesne agenty głosowe pozwalają na komunikację w czasie rzeczywistym z minimalnymi opóźnieniami. Pozwala to przenieść automatyzację procesów na zupełnie inny poziom. Pragniemy zaprezentować bota HR zbudowanego z wykorzystaniem platformy ElevenLabs. Celem naszego rozwiązania jest wsparcie procesu rekrutacji poprzez zastąpienie formularzy i testów kompetencyjnych interaktywnym dialogiem, w którym to algorytm dostosowuje poziom trudności pytań do odpowiedzi rozmówcy.

Bartek Kolasa:
"It’s a match! AI, rekrutacja i czemu to nie jest takie proste"

Rekrutacja do startupów i na C-level to dziś bardziej swatanie niż sprawdzanie kryteriów. Wymagania są nieweryfikowalne, sygnały jakości ukryte między wierszami, a oczekiwania founderów bywają z innej planety. Jednocześnie AI Act i RODO stawiają AI w rekrutacji twarde granice: przejrzystość, nadzór człowieka, zgoda kandydata. Czy AI może być dobrym swatem i nie przekroczyć granic?

******
Uczestnik, dokonując zgłoszenia na wydarzenie, wyraża zgodę na nieodpłatne utrwalanie swojego wizerunku podczas jego trwania oraz na wykorzystanie tych materiałów w celach promocyjnych organizatora tj. WAIT - Wrocław AI Team, w tym na publikację zdjęć na portalach społecznościowych.