Series

Anthropic API

Structured Output — When to Use Prompting vs. Forced Tool Use
Most LLM features eventually need the model to return structured data like a JSON object your application can parse and act on. Connecting LLM output to a database, a UI component, or a downstream API
Jun 6, 20264 min read
Building RAG from Scratch — Embeddings, pgvector, and a Bug Worth Knowing
RAG sounds complex until you break it into its actual steps: Query → embed query → search vector store → retrieve top N chunks → prompt + chunks → generate At its core, it's a retrieval problem with
Jun 4, 20265 min read
Tool Use — How the Model Calls Your Code (And What It Never Sees)
One of the most important things to internalize about LLM tool use is what the model actually does (and doesn't do) when it "calls" a function. Anthropic never executes your code. The model reads the
Jun 3, 20265 min read