Staging environment
Free Lesson

Making LLM Agents Observable & Debuggable

Part of Maven Rewind

30 min
Oct 16, 2025 7:00 PM
Virtual (Zoom)

In this video

What you'll learn

How to debug and monitor agent behaviour in real-time

LLM agents fail silently, hallucinate, and drift: learn to catch issues early with output checks, trace logs, & metrics.

Work with human annotations and LLM's-as-a-judge

Use humans and LLMs to evaluate outputs with real-world workflows and practical examples you can apply immediately.

Using MCPs to level-up your vibe coding with telemetry

Give your IDE eyes and ears using Opik MCP to add telemetry and metrics, so you can spot and fix AI issues fast.

Start building today with open-source cookbooks

Get hands-on examples that work across LLMs and agent frameworks—apply these methods in your stack right away.

Why this topic matters

As LLM agents take on complex tasks—long chats, memory, multi-step tools—traditional model evals fall short. Failures go undetected, costing time, trust, and money. Opik is an open-source platform that brings observability to agents: test behavior, trace actions, and improve performance continuously. Learn how to debug smarter and ship more reliable AI systems.

You'll learn from

Hugo Bowne-Anderson

Hugo Bowne-Anderson

Podcaster, Educator, DS & ML expert

Claire Longo

Claire Longo

AI Researcher at Comet | Mathematician | Startup Advisor | ex-Arize AI 📈

Yale University
Twilio
Opendoor
See all products from Hugo & Stefan