Beginner Lessons

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

How Agent Memory Will Change Your Organization

AI traces are worth a thousand logs

Iterating on Your AI Evals // Mariana Prazeres // Agents in Production 2025

AI Learns Better With Documentation

How Reinforcement Learning can Improve your Agent

Knowledge is Eventually Consistent // Devin Stein // MLOps Podcast #335

Prepare Your Data for AI Now, or You're Screwed Later

What a 120 Billion Dollar CEO thinks about AI

AI Coding Agents Change Software Development Forever

Real-time Feature Generation at Lyft // Rakesh Kumar // MLOps Podcast #334

MLflow 3.0: The Future of AI Agents

Local Ventures Are Thinking Way Bigger

Is AI Just a Fancy Carriage Without the Horse?

Inside Uber's Advanced AI and Machine Learning Platform

Robots Are Learning—But Not Listening

3 to 1,000 Use Cases

Building AI that Doesn’t Break

Inside Uber’s AI Revolution - Everything about how they use AI/ML

Busting the Big AI Myths

Auto Complete by Day, Batman by Night

Easy For Humans but Hard for AI

Not Every AI Agent Needs to Be Loud, Some Just Get the Job Done

Testing AI Intelligence: The Benchmarking Battle

Accuracy and the Right Amount of Fraud

The Creator of FastAPI’s Next Chapter // Sebastián Ramírez // MLOps Podcast #324

Packaging MLOps Tech Neatly for Engineers and Non-engineers // Jukka Remes // MLOps Podcast #322

Going end-to-end

Real Talk: The Expectations of Machine Learning Products

ML/AI Maturity Expectations

Optimizing RAG: A Guide to Configuring Chunks and Metrics

How Product Metrics Become LLM Evaluations

The Great GPU Drought: What We Learned

Getting AI Apps Past the Demo // Vaibhav Gupta // MLOps Podcast #319

The Hidden Struggles of Cloud Integration in Big Orgs

Finding Hidden Gold in AI’s Blind Spots

AI: Different Abilities, Not Less Intelligent

The Intriguing Lens of Language Models

MLOps with Databricks // Maria Vechtomova // MLOps Podcast #314

AI Agents for Financial Institutions // Vamsi Saladi // Agent Hour

Evaluation of Agentic System // Aditya Gautam // Agent Hour

The Future of Data Engineering Lies in AI

Iceberg, MCP, and MLOps: Bridging the gaps for Enterprise // Mini Summit #11 // Snowflake

Behavior Modeling, Secondary AI Effects, Bias Reduction & Synthetic Data // Devansh Devansh // #311

Why 'Vibe Coding' Can Lead to Trouble

How MLOps Helps Drive Ideas from Concept to Cash

A-MEM: Agentic Memory for LLM Agents // April Reading Group

The Annotator’s Dilemma — Experts Know the Truth