MLOps.community Courses

Tricks to Fine Tuning - Advanced Techniques for Model Training Without Labels

Explore Tao fine-tuning techniques with Prithviraj Ammanabrolu as he breaks down this innovative approach using reinforcement learning and synthetic data to help models self-improve without labeled data.

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

AI Agents for Financial Institutions

Explore the complexities of building AI Agents for financial institutions, focusing on scalable architecture to meet the demands of banks, credit unions, and fintechs.

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

Evaluation of Agentic Systems

Explore the structured approach to evaluating complex AI agents with Aditya Gautam, covering essential principles, methods, and metrics for meaningful assessment of agentic systems beyond standard evaluation techniques.

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

Build a Slack Agent with Pydantic AI - Step-by-Step Tutorial

Discover how to build an intelligent Slack digest bot using Pydantic AI that automatically finds and summarizes important threads, keeping you informed without the overwhelm in noisy channels.

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

RAG from Scratch with Best Practices

Explore Retrieval-Augmented Generation (RAG) implementation from the ground up, focusing on industry best practices and optimization techniques.

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

Getting AI Apps Past the Demo - MLOps Engineering Practices for Production

Discover practical strategies for moving AI applications from demo stage to production with BAML creator Vaibhav Gupta, covering engineering practices and real-world implementation challenges.

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

Product Metrics are LLM Evals - Making AI Products More Accurate and Reliable

Discover how to build more accurate and reliable AI products by shortening feedback loops, iterating on prompts, and implementing effective LLM evaluation strategies.

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

Everything Hard About Building AI Agents Today

Explore the three critical gaps in human-AI interaction and learn practical evaluation techniques for building production-ready AI agents that move beyond subjective feedback.

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

Evals Aren't Useful? Really? - Why AI Agent Evaluations Determine Real-World Success

Discover why AI agent evaluations—not bigger models—determine real-world success through stress-testing, simulation, and failure iteration with expert insights from Prosus Group.

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

How to Build Agents That Take Action

Discover how to build AI agents that actually execute tasks, not just chat—learn to overcome security, cost, and accuracy challenges while connecting to real tools like Gmail and Slack.

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

How to Self-Host an AI Agent

Explore building secure, private AI agents for regulated enterprises through self-hosting, covering model selection, infrastructure deployment, and implementation strategies.

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

The Future of User Interfaces - AI is Changing Everything

Discover how Machine Experience (MX) Engineering creates AI-optimized interfaces, moving beyond human-designed APIs to build systems tailored for LLM reasoning and reliable tool integration.

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

Smart Agents Start with Smart LLM Choices

Discover how to select the optimal LLM for AI agents through data-driven evaluation of 15 leading models on code understanding tasks, focusing on practical metrics beyond benchmarks.

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

If There's Free Compute, There's Abuse - Fighting Fraud with Lightweight LLM Agents

Discover how to combat platform abuse using lightweight LLM agents that inspect suspicious code repositories without compromising privacy or relying on third-party APIs.

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

Benchmarking Intelligence - ARC Prize and AI Evaluation Strategies

Explore AI benchmarking strategies, from human-easy puzzles that challenge models to measuring intelligence through learning speed and the philosophical quest toward AGI.

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