Learn AI, Data Science & Business — Earn Certificates That Get You Hired
The Fastest Way to Become a Backend Developer Online
Overview
Build a Learning Habit
Download Class Central's free printable study calendar
Download for Free
Explore the current state of Model Control Protocol (MCP) observability in this 17-minute conference talk from the AI Engineer World's Fair. Learn about the observability challenges that arise as MCP gains adoption and more agent code runs outside your direct control, creating developer experience and monitoring difficulties. Discover the observable.tools initiative and gain insights into where the field currently stands and what developments to anticipate. Follow along with a practical example of an MCP tool usage evaluation framework from mcp.run, presented by Alex Volkov from Weights & Biases, an AI evangelist and founder of the ThursdAI newsletter and podcast, alongside Benjamin Eckel, co-founder and CTO of Dylibso with over a decade of software engineering experience and previous leadership roles at Recurly and Datadog.
Syllabus
The State of MCP observability: Observable.tools — Alex Volkov and Benjamin Eckel, W&B and Dylibso
Taught by
AI Engineer