MLOps.community Courses

Why You Should Care About Observability in LLM Workflows

Discover real-world patterns for building production-ready AI microservices with LangGraph, FastAPI, and OpenTelemetry observability for compliance workflows like HACCP and FDA traceability.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Evaluating AI Agents - Why It Matters and How We Do It

Discover essential strategies for evaluating AI agents in business applications, covering reliability, safety metrics, and practical testing approaches for non-deterministic systems.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

What It Takes to Run Multi-Agent Systems

Discover the infrastructure blueprint for scaling multi-agent AI systems, covering hybrid edge-cloud strategies, low-latency coordination, and data-local compute requirements.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Big Updates to MLflow 3.0

Discover MLflow 3.0's new features for generative AI accountability, including enhanced monitoring, intelligent agents, and structured workflows to keep AI systems reliable and honest.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

9 Commandments for Building AI Agents

Discover practical principles for building effective AI agents that actually deliver results through smart planning, memory systems, and adaptive learning strategies.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

AI Coding Agents Change Software Development Forever

Discover how AI coding agents are transforming software development through expert insights on verification, debugging, and collaboration challenges.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

The Rise of Sovereign AI and Global AI Innovation in a World of US Protectionism

Explore how nations are building AI sovereignty to control their data and infrastructure amid US protectionism, featuring insights on global AI innovation and government AI adoption.

• YouTube
• 54 minutes
• Self-Paced
• Free Video

Too Much Lock-in for Too Little Gain - Agent Frameworks Are a Dead-End

Discover why agent frameworks create unnecessary lock-in and learn composable GenAI patterns for building production-ready agentic systems without vendor dependencies.

• YouTube
• 36 minutes
• Self-Paced
• Free Video

How Agent Memory Will Change Your Organization

Discover how agent memory systems can revolutionize organizational knowledge management by solving the challenge of keeping information current and accessible.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

APICA - The Digital Colleague at the Port of Antwerp-Bruges

Discover how the Port of Antwerp-Bruges built APICA, a multi-agent AI platform that acts as a digital colleague in Microsoft Teams, coordinating specialized agents for complex tasks.

• YouTube
• 20 minutes
• Self-Paced
• Free Video

From Spikes to Stories - AI-Augmented Troubleshooting in the Network Wild

Discover how AI and LLMs transform network troubleshooting by converting complex telemetry data into clear, contextual insights that accelerate fault isolation and reduce downtime.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

Fast, Trustworthy, Reliable Voice Agents - MLOps That Blend LLM Annotation with Human QA

Discover how to build low-latency, high-accuracy voice agents using MLOps pipelines that combine LLM synthetic labeling, human-in-the-loop QA, and model distillation techniques.

• YouTube
• 17 minutes
• Self-Paced
• Free Video

The Hidden Infrastructure Behind Every AI Agent

Discover the critical AI Gateway infrastructure powering modern AI agents, covering dynamic routing, cost-aware load balancing, model failover, and observability patterns.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Voice Model Performance Optimization - Agents in Production 2025

Discover optimization strategies for Whisper and Orpheus models to achieve low-latency speech-to-text and text-to-speech in real-time AI agent applications.

• YouTube
• 17 minutes
• Self-Paced
• Free Video

AI Traces are Worth a Thousand Logs - Understanding and Debugging AI Agent Behavior

Discover how structured AI traces provide complete narratives of agent execution, enabling rapid debugging, robust evaluation, and reliable autonomous system development.

• YouTube
• 15 minutes
• Self-Paced
• Free Video