Mindstone Berlin February AI Meetup
Welcome to the biggest Practical AI Meetup in Berlin!
Join us once a month as we explore the world of artificial intelligence, its cutting-edge practical applications, and the astonishing projects that are shaping our future.
Why should you attend?
- Get up close and personal with the AI projects that are redefining the boundaries of technology and human potential.
- Learn from the brightest minds in the field and gain valuable insights into the ever-evolving AI landscape.
- Unleash your curiosity, fuel your creativity, and expand your network as you connect with fellow AI aficionados and pioneers.
What you can expect?
Mindstone events consist of three talks covering different aspects:
- What I Learned Building With LLMs: A technical talk breaking down the process for building a product using AI with real-life learnings and insights.
- How To Be More Productive Using AI: A practical demo and step-by-step guide on how to use AI to speed up and improve tasks.
- What Does The Future Look Like With AI?: A theoretical talk on the impact of AI on work, life and society.
After the talks we'll have pizza, drinks, and time to connect with everyone around you.
Don't miss the opportunity to see what's really happening in AI - you'll be surprised at what's already possible today.
We have limited spots available, so get your ticket ahead of time to avoid disappointment!
Agenda
Doors Open
Welcome to the event
Introduction
Welcome and event introduction
Deconstructing AI Agents: How to Build Workflows that are 3x Cheaper and More Reliable by Guillaume Duvernay
AI Agents are powerful, but they often suffer from "context inflation," high costs, and unpredictable outputs. In this session, we will demonstrate how to audit your AI architecture and convert complex Agents into deterministic AI Workflows. Using n8n as our playground, we will dissect a standard RAG Agent, identify four key areas of inefficiency, and rebuild it into a streamlined workflow. You will leave with actionable guidelines on when to abandon the "Agent" model for a workflow, and how to significantly optimize tool calls and token usage when an Agent is truly necessary. Key Takeaways: \* Identifying the 4 common inefficiencies in Agent-based RAG architectures. \* Live demo: Refactoring an n8n Agent into a faster, cost-effective workflow. \* Techniques to optimize Agent tool calls using structured sub-workflows.
How to use the AI Problem Framing Canvas to capture and compare AI ideas by John Vetan
Most teams don’t struggle to come up with AI ideas. They struggle to pick the one worth building. In this talk, you’ll see how the AI Problem Framing Canvas helps teams lay out several ideas at once, stress-test them with the same set of questions, and compare them on consistent measures—so you can move faster toward the idea that’s worth building and drop the ones that only sound good on paper. The payoff: less time spent on weak bets, clearer AI decisions, and better thinking across the team. Even the person pitching the idea learns how to frame it well, which raises the bar for every idea that follows.
From Roll-Out to Enterprise Impact: Lessons Learned Scaling GenAI & Agentic Platforms
Many enterprises have started rolling out GenAI and AI platforms at scale. The harder challenge is turning that scale into sustained impact. In this session, we share key lessons learned from supporting large organizations in adopting GenAI and agentic platforms at scale. The focus is on what enables impactful AI transformation beyond the technical rollout: the steps that matter, the decisions that unlock adoption, and the conditions required to turn promising technology into sustained business impact.
Wrap Up
Closing remarks and next steps
Pizza, Drinks & Networking
Casual networking with food and drinks
Speakers
Attendees
Location