Skip to content
WorkshopIn personPast event

The AI Agent Workshop: Paris

Event artwork for The AI Agent Workshop: Paris

This event has ended

This listing is kept as an archive. Explore upcoming events to find your next one.

See upcoming events in Paris
About this event

What to expect

Join leading AI engineers at STATION F in Paris for a hands-on, half-day workshop focused on building self-improving AI agents. Hosted by Weights & Biases, this intensive session takes you beyond basic agent development into the cutting edge of agentic AI: autonomous systems that continuously learn and improve through reinforcement learning.

What You'll Build

This isn't a theory-only workshop — you'll get hands-on experience building production-ready AI agents. The programme is structured around two complementary sessions that take you from specialized model training through to full agent deployment.

Session One: ART-E-Mini focuses on using reinforcement learning to specialize open-source models for real-world tasks. You'll build an agent that searches actual emails, evaluate its initial performance, then dramatically improve its reliability using serverless RL on CoreWeave GPUs. The session demonstrates how to define structured tasks that prevent model drift whilst enabling cost-effective continuous improvement — a critical capability for production agents.

Session Two: From Brains to Body teaches you how to transform your specialized model into a fully-capable agent. You'll learn to implement agent skills, tool use, Model Context Protocol (MCP) integrations, and robust evaluation pipelines using W&B Weave. This session connects your model's "brain" to the "body" it needs to interact with real systems and users.

Who Should Attend

This workshop is designed for AI engineers, ML practitioners, and AI researchers who want to move beyond static models into the realm of self-improving agentic systems. You should have familiarity with LLMs and basic ML concepts, but you don't need prior experience with reinforcement learning or agent frameworks.

Key Takeaways

  • Build and evaluate open-source LLM-powered agents on real-world tasks
  • Apply serverless reinforcement learning to continuously improve agent performance and reliability
  • Design structured task and evaluation pipelines to prevent model drift
  • Architect production-ready agents with tool use, MCP integration, and skills frameworks
  • Implement iterative evaluation workflows for cost-efficient, self-improving agents

The workshop runs from 12:00-6:00 PM, giving you an intensive afternoon of learning and building alongside the Weights & Biases team and fellow AI practitioners. You'll leave with practical experience in

Running an AI event in Paris?

List it here, free.

Meetups, workshops and conferences go in front of thousands of builders after a quick review.

List your event