⚡ Why You Shouldn’t Miss This

Welcome to the next Paris edition of AI Tinkerers—where every attendee ships code and every talk dissects the guts of modern AI systems. On Thursday, June 26 from 19h00–22h00, we’re teaming up with Google Cloud AI and Theodo for a hands-on look at agents, graph workflows, and long-context LLMs that quietly power the tools you use every day.

Capacity is capped at 50 builders and our last three Paris meetups filled in quickly, so lock your spot now and—if you have something spicy—submit a demo while you’re at it.

Google Cloud accelerates every organization’s ability to digitally transform its business and industry.

🗓️ Practical Details

• Date / Time: Thursday, 26 June 2025 · 19h00 – 22h00
• Location: Paris, France (full address revealed upon acceptance)
• Registration: Fill out the quick form above (GitHub / LinkedIn link required)
• Speaker & Demo Form: See “Submit Your Demo or Talk Proposal” after RSVP

🎤 Talks & Live Demos

Intelligent Agents, the New Frontier of LLMs

Guillaume Laforge – Developer Advocate, Google
Discover how Gemini-powered agents change application architecture, decision orchestration, and user experiences.

Building Knowledge Graphs with Gemini

Laurent Picard – Developer Relations Engineer, Google Cloud
Large language models have transformed natural language problem-solving. However, LLMs often have limitations regarding the inputs they can process. Let’s see how we can extract insights from extensive text inputs (up to 1M tokens) and automatically construct knowledge graphs.

From Monolith to Modular: Mapping 500 k LoC with AI & Graphs

Thomas Walter – Group Partner Healthtech & CTO, Theodo France
See how AST-parsing + GenAIScript + Neo4j converted days of code archaeology into a one-hour graph.

GraphRAG Architecture

Laurent Tandé – Senior Solution Engineer, Neo4j
Understand how to scale Retrieval-Augmented Generation with knowledge graph backends and graph reasoning to improve precision and transparency of LLM pipelines.

Compar:IA – Chatbot Arena Dataset

Simonas Zilinskas – Compar:IA Deployment Manager, Ministry of Culture (France)
Explore how dataset curation and annotation from real-world interactions fuels the evaluation of government-grade conversational agents.

NANDA: Internet AI Agents

Serge Vasylechko – AI Researcher, Harvard
Dive into an experimental framework for deploying multi-agent systems on real websites, coordinating tasks and learning across the open web.

BâtiChat: AI Building Assistant

Yiying Yu – Founder, BâtiChat
Discover how a multi-agent AI assistant uses building and urban data to answer questions, provide urban codes, and generate 3D building models from any address.

Streamlit: AI Football Performance

Claudio Chaves – Director, Client Success, HUB Americas at UiPath
A live demo of how UiPath + Streamlit + LLMs analyze football player performance and generate scouting reports with explainable metrics.

👩‍💻 Who Gets In

AI Tinkerers is 100 % active builders—ML engineers, researchers, prompt/vibe coders, indie hackers—not passive spectators. If you can demo running code, you’re our people.

🚀 How to Participate

1. RSVP now—spots go fast.
2. Optionally submit your demo via the speaker form right after registering.
3. Show up, share, and learn from fellow builders.

🤝 Sponsors

Google Cloud is the new way to the cloud, providing AI, infrastructure, developer, data, security, and collaboration tools built for today and tomorrow. Google Cloud offers a powerful, fully integrated and optimized AI stack with its own planet-scale infrastructure, custom-built chips, generative AI models and development platform, as well as AI-powered applications, to help organizations transform. Customers in more than 200 countries and territories turn to Google Cloud as their trusted technology partner.

Theodo - Founded in 2009, Theodo is a global design and software engineering consultancy with a team of 700 people. They specialize in creating innovative digital solutions, including web and mobile applications, leveraging deep expertise in cloud-native technology and agile delivery methods like Lean, Scrum, and DevOps. As part of the Theodo Group, they collaborate across a network of 10 specialized companies, focusing on various sectors and driving digital transformation for businesses worldwide, ensuring high-quality work and long-term improvements for their clients.

🛠️ Builder Stats (auto-updated)

• Attendees: This exclusive community of 4,082 subscribers comprises elite technical professionals, with 42% specializing in AI/ML research, 31% in full-stack software engineering, and 27% in technical leadership. Members possess deep expertise in PyTorch, LLMs, and agentic architectures. Notably, the group features prominent open-source maintainers from Hugging Face and graduates from top-tier institutions like École Polytechnique.
• Companies Represented: Featuring tech giants like Google, Meta, and Microsoft, alongside open-source and AI leaders such as Hugging Face, Mistral AI, LangWatch, and Black Forest Labs, and innovative startups like ElevenLabs, Docker, Datadog, Algolia, and Zoom, and more
• Demos Submitted: Across 130 submissions, 83 demos have been presented at AI Tinkerers - Paris. The most exciting themes have focused on agentic production workflows, knowledge-graph-driven reasoning (GraphRAG/context graphs), and system architectures for scalable, reliable deployments. Technically, structured outputs and tool/function calling, cost/latency reductions, eval/benchmarking, and multimodal/local execution have been repeatedly explored.
• Testimonials:

  “Overall, it was high-quality content and it made me want to come back for the next ones!”

  — Product manager, AI community

  “Great organization, partners and food! Lovely folks and good industry insights”

  — ML engineer, happtiq

  “It was all really good...”

  — AI engineer, finance

  “Having so many volunteers involved from the community was exceptional...”

  — AI consultant, NLP

  “Engaging, open to further discuss experiences.”

  — Full-stack web developer

  “Great event, thank you very much!”

  — AI engineer, finance

  “Having 7 demos in 6 hours or of such a small group semt exceptional...”

  — AI consultant, NLP