• RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
• chunking — Splitting documents into passages small enough to embed and retrieve individually — the step that quietly determines whether retrieval works at all.
• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Names the recurring cost of skipping foundations — badly reinvented RAG chunking, duplicate agent eval schemes, messy context management — and argues for pairing courses with building rather than choosing one.

• postBuilding AI Startups at Agent Speed: The YC Startup School Talk
• postWhy Telling People Not to Learn to Code Ages Badly
• postThe Product Management Bottleneck in Agentic Coding
• postParallel Agents as the Next Axis for Scaling AI

• articleThe AI application skill stack: grounding, agent loops, evals, productionAndrew Ng
• postError Analysis Is the Real Speed Limit on Agent DevelopmentAndrew Ng
• articleA Field Guide to Rapidly Improving AI ProductsHamel Husain

Checking sign-in…

Loading comments…