Blogs
Short, sharp pieces from the people who write the courses: what broke, what worked, and what we would do differently.
6 posts
Why Do GPUs Matter So Much for AI?Behind every large AI model is a massive amount of computation. Discover how GPUs make that computation practical and efficient.7 min readHarness Engineering: How to Build Reliable AI AgentsHarness Engineering is about designing the environment around AI agents with the right context, tools, constraints, verification, and feedback. It turns powerful models into reliable, controllable systems that can complete real-world tasks safely.5 min readEvaluating AI Applications: How to Measure RAG and Agent QualityLearn how to evaluate RAG systems and AI agents using quality metrics, datasets, human review, LLM judges, regression tests, and release decisions.19 min readAI Agents Explained: How LLMs Use Tools to Complete TasksAI agents use LLMs to understand goals, make decisions, and use tools to complete tasks through planning, actions, and real-world workflows.9 min readLLMs vs. SLMs: How to Choose the Right Model for Your AI ApplicationMonitor and debug LLM applications with logs, metrics, and traces. Learn to identify latency, retrieval failures, tool errors, rising costs, and AI-specific issues in production.15 min readAI Observability: How to Monitor and Debug LLM ApplicationsMonitor and debug LLM applications using logs, metrics, and traces. Learn how to identify latency, retrieval failures, tool errors, costs, and other production issues in AI systems.14 min read