Marcelo Trylesinski

Self-healing agents sound inevitable: an agent fails, understands what went wrong, proposes a fix, validates it, and improves the system. But without observability, self-healing is just guessing. This talk explains why reliable agent improvement needs a feedback loop built on traces, evaluations,...

After months maintaining the MCP Python SDK, I’ve seen common architectural pitfalls. This talk covers designing scalable tool boundaries, maintainability, and testing strategies. Learn to avoid antipatterns and prepare for the v2 SDK migration. Leave with a clear design framework for your server.

In this talk, we will explore how the integration of PydanticAI and Logfire creates a powerful foundation for generative AI applications. We'll demonstrate how these tools combine to form sophisticated AI workflows and give you comprehensive monitoring. The session illustrates how PydanticAI...

In this talk, we will explore how the integration of PydanticAI and Logfire creates a powerful foundation for generative AI applications. We'll demonstrate how these tools combine to form sophisticated AI workflows and give you comprehensive monitoring.

FastAPI has become one of the most popular web frameworks in Python, but do you know how it really works internally? In this talk, we'll go through each FastAPI component, and understand when they run. We'll also understand how FastAPI interacts with Pydantic, Starlette and Uvicorn!

From the team behind Pydantic, Logfire is a new type of observability platform built on the same belief as our open source library — that the most powerful tools can be easy to use.

FastAPI has been growing a lot lately, but people aren't really aware of the packages that were the basis for its foundation. On this talk, we are going to explore Starlette, the web framework on which FastAPI is built on top of. 🚀