Browse Lessons

Evals are your moat

Is Open Source Software Actually Secure?

Before Building AI Agents Watch These Hard Earned Lessons

Exposed: Biggest Mistake Marketers Make

AI-Powered Sales, Human Connection

Companies Leverage Stack Overflow Internally

“Our best evals come from pizza parties”

LLMs decay fast but we still train them

Catastrophic agent failure and how to avoid it // Edward Upton // Agents in Production 2025

Zero Trust for Multi-Agent Systems // Surendra Narang | Venkata Gopi Kolla

AI’s Hidden War Revealed

Smarter Data, Faster Applications

The Era of AI Agents in Marketing // Joel Horwitz // MLOps Podcast #337

The Future of Compute: How AI Agents Are Reshaping Infrastructure

Advancing the Cost-Quality Frontier in Agentic AI // Krista Opsahl-Ong // Agents in Production 2025

Cutting Costs with Artificial Intelligence

Small Language Models are the Future of Agentic AI Reading Group

A Deep Discussion with the Author of "Context Rot"

Developer Productivity

Updating rows with AI effectively

Devs Trust AI Code Less

Primary Metric is saving human time

Vibe coding tricks part 1

The Future of User Interfaces: AI is Changing Everything

Building Real-Time, Reliable Voice AI: From Simulation to Production //Brooke Hopkins | Peter Bakkum

How to Self-Host an AI Agent

Smart Agents Start with Smart LLM Choices // Shai Rubin // Agents in Production 2025

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

Distilling 200+ Hours of NeurIPS: What’s Next for AI // Nikolaos Vasiloglou // MLOps Podcast #336

Too much lock-in for too little gain: agent frameworks are a dead-end // Valliappa Lakshmanan

How Agent Memory Will Change Your Organization

From Spikes to Stories: AI-Augmented Troubleshooting in the Network Wild // Shraddha Yeole

The Hidden Infrastructure Behind Every AI Agent

Fast, Trustworthy, Reliable Voice Agents: MLOps That Blend LLM Annotation with Human QA// Erik Goron

Using humans as tools for agents

Make your prompts longer and give more context

Don't create different products within the same product

AI traces are worth a thousand logs

Voice model performance optimization // Madison Kanna // Agents in Production 2025

a process for finding the best os models #podcast #aiinfrastructure

Creating your own AI eval set #podcast #aiinfrastructure #ai

Leverage Stack Questions in LLM

Questions on Stack Overflow These Days

Why Not Build Cursor

Deploying Executable Agent Workflows

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

APICA: The Digital Colleague at the Port of Antwerp-Bruges // Pierre Gerardi

Integration of AI into Traditional Systems // Hakan Tek // Agents in Production 2025