AI agents are everywhere, but how do you go from demo to dependable? In this talk, we’ll build agents using LangGraph, and take it beyond toy examples into enterprise-grade readiness.

We’ll start with context engineering concepts like: control flow, prompt engineering, prompt management and tool calling. From there, we’ll build an agent step-by-step, enabling contextual reasoning via Retrieval-Augmented Generation (RAG), and integrating tool use for dynamic task execution. We'll also cover agent observability with open source observability tools such as LangFuse to bring full observability into the decision our agents make.

Whether you're exploring AI agents or planning your first production deployment, you'll leave this session with the patterns, tools, and clarity to do it right.

Highly available, scalable, durable, and distributed asyncrounously long-running workflows are the core of Nous' switching business.

Having a powerful orchestration engine is critical and our journey has been a long one.

Come and listen to how and why we integrated Temporal.io as our core way to deterministically run our core business logic.

Ces dernières années, le SQL a beaucoup évolué, et vous voici équipé·e d’une batterie de fonctionnalités et de moteurs de base de données utiles pour vos développements ou vos livraisons en mode continu.

Cette session vous aidera à réaliser vos projets Ainsi, vous verrez la démonstration des possibilités de déployer, de communiquer et de synchronisation des données, tout en gardant les capacités de communiquer avec votre projet.

We'll first explore how we implemented our MCP server for GraphQL APIs and then use Grafbase extensions to federate non-GraphQL datasources to have them all available for agents without increasing the number of tools.