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.

In an era where everything even slightly related to generative AI is considered the new meta, it is hard to keep track of the technical increments that are actually useful to our work and domains. The announcement of the Model Context Protocol from Anthropic has generated a lot of buzz and is a good attempt to become the leader among the various LLM providers. This talk will take a stab at creating an overview and an honest take on what the MCP server will bring us and what it feels like to develop one for Mollie, trying to combine all emotions and experiences together to answer the question of whether it really lives up to the promise. Defying established presentation best practices, I will try to live-code a new MCP server providing functionality for a to-be-chosen service.

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.

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.