Happy Friday! We know – Fridays can be slow. The week’s been long, the energy is fading, and the weekend can’t come soon enough.

Well, we’ve got just the thing to fix that.

The Agentic Conf Hamburg 2026 after movie is here – and we promise it’ll put some energy back into your Friday.

👉 Watch the After Movie on YouTube

Thank You – To All of You

This video is our big thank you to everyone who made Agentic Conf Hamburg 2026 what it was.

To our 250+ attendees – you showed up with curiosity, energy, and the kind of conversations that make a conference truly special. You are this community.

To our 25+ speakers and workshop leaders – you didn’t deliver polished marketing talks. You shared real experiences from real projects, honest lessons learned, and genuine insights. That’s what makes this community different.

To our sponsors – Vorwerk, adesso insurance solutions, Auto Fleet Control, INNOQ, hackers&wizards, Digitale Leute School, and Tegtmeier Internet Solutions – your support made it possible to bring this community together. Thank you for believing in what we’re building.

To our volunteers – the ones who showed up early, stayed late, and handled a thousand things nobody noticed. You are the backbone of this event.

Watching this video back, we’re reminded why we started Agentic Hamburg in the first place: to bring together the people who are shaping how we build software with AI. And on March 22nd, that’s exactly what happened.

Hit play. Relive the day. And have a great weekend.

👉 Watch the After Movie on YouTube

We’re happy to share the video of Björn Rochel’s talk from Agentic Conf Hamburg 2026!

The Talk: You Don’t Need a Bigger Model. You Need a Better AI Harness

Björn showed us how he built Credfolio2 – a full-stack professional portfolio application with a Go backend, Next.js frontend, GraphQL API, background job queues, and LLM extraction pipelines – without writing a single line of code. All 77,000 lines were written by Claude Code, steered by him. Three weeks, 298 commits, one person.

But the talk wasn’t about the output – it was about what made it possible.

Björn walked us through the AI development harness he built to get predictable, high-quality results from an agentic coding tool. From a sandboxed devcontainer for autonomous agent operation to a CLAUDE.md that acts as persistent architectural memory, session hooks, specialized subagents, Architecture Decision Records, a markdown-based issue tracker, and five enforcement hooks that block broken commits – every piece was a context management strategy in disguise.

The key takeaway: you don’t need a bigger model. You need better systems thinking. You’re not pair programming – you’re architecting the environment in which AI operates.

Watch the Talk

👉 Watch on YouTube

Follow Björn on LinkedIn.

We’re excited to announce Xesca Alabart as a speaker at Agentic Conf Hamburg on March 22nd!

About Xesca

Xesca Alabart has spent 15+ years as CTO in fintech, insurtech, and media. She led the tech for MotoGP at Dorna, worked on crypto banking at SEBA (now AMINA Bank), and built insurance platforms at Bolttech. Now she’s the founder of Gluecharm, rethinking how software requirements should work in the AI era.

The Talk: Requirements-Driven Development: The Missing Layer in Agentic Coding

For decades, the bottleneck in software development was coding. We threw everything at it — better languages, frameworks, DevOps, CI/CD, cloud infrastructure — all to make the engineering phase faster and more reliable. And it worked.

Now, with agentic coding tools and AI-assisted development, that bottleneck is dissolving faster than anyone expected. Code generation is becoming near-instantaneous. But this acceleration has exposed a deeper problem: we’re still terrible at defining what to build. Ambiguous requirements, lost context between business and engineering, specs that decay the moment they’re written. When coding was slow, these gaps got patched along the way. When coding is instant, they become catastrophic. You can now build the wrong thing at unprecedented speed.

In this talk, Xesca shares how Gluecharm is addressing this new reality with an AI-native requirements management platform built on 150+ specialized micro-agents and knowledge graphs. She’ll walk through why traditional requirements practices can’t keep pace with AI-accelerated development, how “Application Maps” preserve business context across the full lifecycle, and what it takes to build the missing layer between business intent and working code.

See Xesca Live

Catch this talk and many more at Agentic Conf Hamburg on March 22, 2026 at SAE Institute Hamburg.

👉 Get your tickets on Luma

We’re excited to announce Fabian Meyer as a speaker at Agentic Conf Hamburg on March 22nd!

About Fabian

Fabian Meyer is Chapter Lead Vue at eventim Tech. He leads the Vue chapter developing frontend engineers and has the technical leadership for the eventim.Tixx online shop, where he shapes a scalable platform built to meet the highest standards in ticketing for 100+ customers. He is deeply invested in agentic engineering and AI-driven workflows, enabling teams to rethink how they build software.

The Talk: Onboarding Your Agent: How eventim Integrates Agentic Engineering into Enterprise Workflows

Coding agents are impressive, but in enterprise environments code was never the main bottleneck. The friction lives in the process: turning tickets into specs, running pipelines, opening merge requests, deploying, and debugging failures.

At eventim, they onboarded their agent like a new engineer. They gave it access to GitLab and Jira, implemented their workflows as agent skills, and let it operate within their guardrails — from ticket to verified result. Engineers review outcomes, not execute steps.

This talk introduces the four pillars that enable this: Specification, Implementation, Tools, and Verification — and why in agentic engineering, the best engineers write the best specs.

See Fabian Live

Catch this talk and many more at Agentic Conf Hamburg on March 22, 2026 at SAE Institute Hamburg.

👉 Get your tickets on Luma

We’re excited to announce Wolf Brüning as a speaker at Agentic Conf Hamburg on March 22nd!

About Wolf

Wolf Brüning is Lead UX Designer B2B at OTTO, where he also works as a Product Discovery Coach and founded their internal “Discovery School” training format. With deep insights into how Product Discovery is implemented across OTTO’s roughly 100 product teams, he knows which methods and frameworks help, what can go wrong, and how to tackle new developments like AI.

The Talk: Build the Right AI Product: The Good, the Bad and the Ugly of Product Discovery in the AI Era

In this talk, Wolf explores the changes AI can — or might — bring about in Product Discovery. What have they tried and learned so far? Where can AI take us further and which paths are dangerous to take? The talk underlines the importance of Product Discovery in modern product development, takes a generally optimistic stance on AI, but also encourages critical thinking at the intersection of business value, user value, and technical feasibility.

See Wolf Live

Catch this talk and many more at Agentic Conf Hamburg on March 22, 2026 at SAE Institute Hamburg.

👉 The conference is sold out! Visit agentic.hamburg to stay updated.

We’re excited to announce Leo Peters as a co-speaker (with Benedikt Stemmildt) at Agentic Conf Hamburg on March 22nd!

About Leo

Leo Peters is a Senior Software Developer at Tegtmeier Inkubator GmbH, working across Python development, ML engineering, and computer vision. He studied Software Engineering at HAW Hamburg and has devoted most of his career to understanding computers — starting as a teenager fixing anything with a plug or a battery.

The Talk: Stop Building Features. Build the Factory That Builds Them.

You’ve got your CLAUDE.md, your subagents, your custom skills. And it works. But every feature still starts with you: kicking off the agent, steering it, reviewing, course-correcting. You’ve optimized the tool. You haven’t automated the process.

The real shift is indirection. Instead of using an agent to build a feature, build a production line that builds features for you. Scripts, validation steps, orchestration — from ticket to pull request with minimal intervention. And don’t stop at code. The factory writes tests, generates documentation, handles requirements engineering. Run it in production and let agents react to monitoring data, user feedback, and KPIs. The factory is never done. It grows.

Two hard truths: you can’t copy someone else’s factory, because it’s deeply coupled to your codebase and conventions. And when a new model drops, you rebuild it. That’s the new developer skill: not maintaining one perfect system, but rapidly creating factories for any situation.

No slides. In this talk, Leo will open a real factory from a real client project and walk through how it’s built, how it runs, and why this is the path from AI-assisted to genuinely autonomous.

See Leo Live

Catch this talk and many more at Agentic Conf Hamburg on March 22, 2026 at SAE Institute Hamburg.

👉 The conference is sold out! Visit agentic.hamburg to stay updated.

We’re excited to announce Harshil Agrawal as a speaker at Agentic Conf Hamburg on March 22nd!

About Harshil

Harshil Agrawal is a Developer Advocate at Cloudflare. Working in the Developer Relations team, he enjoys sharing his learnings with the community. A JavaScript developer, open-source contributor, and low-code enthusiast, Harshil loves experimenting with tech and building small projects.

The Workshop: Why, and How You Need to Sandbox AI-Generated Code?

We are using AI to write code and to be more productive. But giving AI access to our machines and letting it run on its own is dangerous. Imagine giving AI access to the server where you run your application! You want users to interact with your app through a chat interface, maybe build their own apps or customize the UI. If not supervised carefully, AI can break your application or worse — leak private data.

So how do you run AI-generated code within your application and allow users to build their own apps? In this workshop, Harshil goes beyond the hype and dives into the practical architecture of sandboxing AI-generated code. You’ll learn how to integrate an LLM to generate code and how to run that code in a secure, isolated environment.

See Harshil Live

Catch this workshop and many more at Agentic Conf Hamburg on March 22, 2026 at SAE Institute Hamburg.

👉 The conference is sold out! Visit agentic.hamburg to stay updated.

We’re excited to announce Christoph Hübner and Waqas Ahmed as speakers at Agentic Conf Hamburg on March 22nd!

About Christoph & Waqas

Christoph Hübner is a Senior Data Engineer at MOIA, specialized in building scalable, high-performance architectures that transform raw data into actionable business intelligence.

Waqas Ahmed is a Software Engineer at MOIA, building developer tooling and automation that scales. He recently migrated 580+ repos across an org in about 2 weeks using agentic orchestration. His interests span developer experience, platform engineering, and making org-wide problems disappear.

The Talk: Driving AI: How MOIA Scales LLM Expertise

Discover how MOIA is moving beyond the hype to integrate Large Language Models into the daily fabric of engineering and operations. This talk dives into their journey of building a cross-functional community of practice where shared experience — from prompt engineering to architectural guardrails — drives real-world efficiency. Learn the specific strategies they use to turn individual LLM experiments into collective, high-impact tools that power the future of urban mobility.

See Christoph & Waqas Live

Catch this talk and many more at Agentic Conf Hamburg on March 22, 2026 at SAE Institute Hamburg.

👉 The conference is sold out! Visit agentic.hamburg to stay updated.

We’re excited to announce Björn Rochel as a speaker at Agentic Conf Hamburg on March 22nd!

About Björn

Björn Rochel is a Senior Engineering Manager and Principal Engineer with a passion for building scalable systems, empowered teams, and lasting engineering culture. He’s both a hands-on architect and an engineering leader – the kind of person who thinks in systems, whether that means code or organizations.

You can follow Björn on LinkedIn.

The Talk: You Don’t Need a Bigger Model. You Need a Better AI Harness

Björn built Credfolio2 – a full-stack professional portfolio application with a Go backend, Next.js frontend, GraphQL API, background job queues, and LLM extraction pipelines – without writing a single line of code. All 77,000 lines were written by Claude Code, steered by him. Three weeks, 298 commits, one person.

The interesting part isn’t the output. It’s what made the output possible.

In this talk, Björn will walk through the AI development harness he built to get predictable, high-quality results from an agentic coding tool. It starts with containment – a sandboxed devcontainer that lets the agent operate autonomously while limiting what it can reach. But the real game is context: an AI agent is only as good as what it can see, and the biggest challenge is making sure the right context is available at the right time.

Expect to see:

• A CLAUDE.md that acts as persistent architectural memory
• Session hooks that prime the agent with the current task on startup
• Specialized subagents running in isolated contexts to keep the main conversation focused
• Architecture Decision Records that capture reasoning the AI can’t carry across sessions
• A markdown-based issue tracker with checklists that double as executable specifications
• Five enforcement hooks that block broken commits and incomplete work

Every one of these is a context management strategy in disguise – reducing noise, surfacing what matters, and compensating for what the model forgets, never knew, or can’t fit in its window.

None of this required a better model. It required better systems thinking. You’re not pair programming – you’re architecting the environment in which AI operates.

See Björn Live

Catch this full talk and many more at Agentic Conf Hamburg on March 22, 2026 at SAE Institute Hamburg.

👉 Get your tickets on Luma

We’re excited to announce Aleksandr Lossenko as a speaker at Agentic Conf Hamburg on March 22nd!

About Aleksandr

Aleksandr Lossenko is a Team Lead Engineering at Phrase.com, based in Hamburg. Born in Tallinn, Estonia, he started programming with Ruby on Rails and gathered 10+ years of experience building complex distributed applications. For the last 3 years, he’s been a full-time Elixir engineer, system architect, and team lead.

The Lightning Talk: How a 3-Day Hackathon Gave Non-Engineers Access to the Codebase at Remote.com

At Remote, the people who need codebase knowledge most — support agents, PMs, sales — are the ones least equipped to read code. Aleksandr’s team built Sherlock App in a 3-day hackathon: a Phoenix LiveView app powered by OpenCode that lets anyone ask questions about the codebase in plain English and get accurate, source-linked answers in seconds.

In this lightning talk, he’ll cover how they went from idea to company-wide deployment: the architecture (GenServer-based SSE streaming, Ash Framework for instant Okta SSO, OpenCode as the AI engine), how MCP servers let Sherlock pull context from Notion and Linear alongside code, and what happened when non-engineers started getting answers without filing tickets or interrupting developers.

See Aleksandr Live

Catch this talk and many more at Agentic Conf Hamburg on March 22, 2026 at SAE Institute Hamburg.

👉 The conference is sold out! Visit agentic.hamburg to stay updated.