An interactive panel exploring how emerging AI tools and models are transforming how developers design, test, and deploy software. Topics include comparing Anthropic vs OpenAI on long-haul tasks and the role of self-hosted LLMs in the SDLC, with insider perspectives on trends and live demos from AI teams.

Everyone’s talking about AI agents! But what are they, and how do you build one? This talk cuts through the hype. Drawing on my experience building a GenAI platform, I’ll show that powerful agents are within reach, no advanced degree required. We’ll define agents simply: LLMs + tools + memory. Then we’ll build an agent with the OpenAI Python SDK, using coding basics you know: functions, loops, and conditions. I’ll show how you can enhance your agent with a knowledge base using Elasticsearch as a tool. By the end, you won't just understand agents; you'll be fully equipped to build your own.

Découvrez comment des outils comme OpenAI, LangChain ou les agents IA sont utilisés dans des produits concrets et comment vous les utiliserez pendant le bootcamp.

Du développement backend aux intégrations d’IA, découvrez comment l’intelligence artificielle transforme la façon dont on crée des logiciels et pourquoi les développeurs capables de construire avec l’IA sont très recherchés

Découvrez comment des outils comme OpenAI, LangChain ou les agents IA sont utilisés dans des produits concrets et comment vous les utiliserez pendant le bootcamp.

An in-depth look at agentic AI — how to build agent-driven applications using the LlamaIndex framework. We’ll cover core design patterns such as event-driven workflows, routing, parallelization, orchestrator–worker setups, and evaluator–optimizer loops, and show how to implement them in LlamaIndex. The talk also explores how these pieces fit together into multi-agent systems, and how MCP servers and tools help agents obtain live context to hit their goals. By the end, you’ll learn to build agents with LlamaIndex, compose multi-agent systems, design reusable tools for agents, and give your agents real-time knowledge. The session uses the open-source LlamaIndex framework in Python and models from providers like OpenAI and Anthropic.

An overview of agentic AI and how to build agentic apps using the LlamaIndex framework. Covers core design patterns such as event-driven workflows, routing, parallelization, orchestrator–worker setups, and evaluator–optimizer loops, and discusses multi-agent systems. The session will explore MCP servers and tools for providing live context to agents, and uses the open-source LlamaIndex Python framework with models from OpenAI and Anthropic.

An overview of agentic AI concepts, focusing on how to build agentic apps with LlamaIndex. We'll cover core design patterns such as event-driven workflows, routing, parallelization, orchestrator–worker setups, and evaluator–optimizer loops, and show how to bring them to life in the LlamaIndex framework. The session also explores how these pieces fit into multi-agent systems, with a focus on MCP servers and tools that provide live context to agents. By the end, you'll learn to build agents using LlamaIndex, compose multi-agent systems, design reusable tools for agents, and give agents real-time knowledge. The talk uses the LlamaIndex Python framework and models from OpenAI and Anthropic.

In this hands-on workshop, you will learn how Knowledge Graphs and Retrieval Augmented Generation (RAG) can help GenAI projects avoid hallucination and provide access to reliable data. Topics include LLMs and hallucination, integrating knowledge graphs, GraphRAG, vector indexes and embeddings, querying graphs with natural language, and using Python and OpenAI to create GraphRAG retrievers and GenAI applications.

Day 5 self-paced session on OpenAI's ecosystem: APIs, assistants, and beyond.

This meeting will focus on real-world use cases. HelloPrint, an online platform for printed products with over 10 million SKUs, leveraged a modern data stack—including DBT, Airflow, and OpenAI—to streamline its product catalog. Our team’s solution reduced manual tasks by 80%, showcasing the power of automation and data-driven processes.

40 minutes + 5 mins questions. À travers des cas d'exemples (notamment des sites automatisés) et des retours concrets (RAG, plateformes...) qu'avons-nous appris quant à la réalisation d'un projet utilisant de l'IA générative ? Comment ces outils d'IA génératives vont impacter nos métiers.... Même les plus créatifs !

Conversation with Andrew Hoh, a long-time product leader at Microsoft, Facebook, and Airbnb, now founder of LastMile AI. Discusses his transition to founding LastMile AI and building a GenAI platform, including features like prompt management, editors, model routing, source control, and evaluation.

Overview of getting started with Generative AI using Azure AI and OpenAI, available through the Founders Hub program credits.

Johannes Nicolai is a long-time open-source enthusiast and contributor. He is interested in all things API design, IssueOps, integrations, CI/CD, and generative AI - check out his GitHub profile (@jonico) to learn more about his projects. In his current role at Postman, he is helping customers in central Europe to adopt API-first best practices and developer workflows established from his time at GitHub and PlanetScale. Before GitHub, he led the local version control teams at CollabNet - the founders of Subversion and SourceForge - so branching and merging everywhere he goes.

The talk is 90 percent a live demo (what could possibly go wrong :-), where we first explore the Postman Public API network to find interesting AI API workspaces like OpenAI and Aleph Alpha (and then find Waldo with the help of AI). We will try out the examples in those workspaces, including Postman's ability to visualize API responses programatically (this is where the lego comes in), use credential helpers for popular APIs and introduce request chaining for more powerful automation ideas. We will close with a Harry Potter-API based example on how to generate non trivial API test cases using postbot - Postman's built-in AI based helper. All functionalities demoed are available in Postman's free plans, so no hidden sales pitches coming ;-)

L'optimisation des temps de résolution d'incidents s'impose comme un enjeu central dans le monde de l'IT. Dans cette perspective, nous explorerons l'observabilité orientée AIOps et verrons comment les ressources Azure, telles que Log Analytics et Logic Apps, couplées à l'API d'OpenAI, peuvent vous aider à automatiser l'analyse des incidents et réduire le temps de leur résolution.

Exploring agents with frameworks like Langchain and vector databases; learn how to build apps that can perform tasks autonomously.

Learn about fine tuning, prompt tuning, guardrails, and middleware to make LLMs more consistent and reliable.

Get introduced to Semantic Kernel for developers, covering essential components such as the kernel SDK, planner, memories, and connectors. Learn through examples and applications.

Learn how to harness the power of Azure OpenAI in Power Apps and Power Automate, tailored specifically for citizen developers. Includes hands-on exercises and real-world examples.