Build with LLM APIs
APIs, RAG, tool use and shipping real AI features.
Courses
Chat with your docs.
Build a RAG Chatbot on Your Own Documents
Ship a chatbot that answers from your PDFs and docs, with citations, using embeddings, a vector store and an LLM API.
Give your AI tools.
AI Agents with Tool Use
Build agents that call your functions, loop until the job is done, and stay inside the guardrails you set.
Tutorials
Build with LLM APIs.
Your first Claude API call in TypeScript and Python
Install the SDK, make a request, stream the answer and cut costs with prompt caching, in about ten minutes.
Build with LLM APIs.
RAG in plain English (and a minimal implementation)
How retrieval-augmented generation lets an LLM answer from your documents, and the smallest version you can build today.
Videos
Tips
Cache your long system prompt
If every API call repeats the same long instructions or document, turn on prompt caching. Repeated input gets much cheaper and faster.
Stream long answers
Stream responses in your app. Users see text immediately and you avoid HTTP timeouts on long generations.
Keep 20 test questions
Before changing a prompt or model in production, rerun a small fixed set of real questions. Vibes are not a test suite.
Overlap your chunks
In RAG, split documents on headings or paragraphs with a little overlap, so an answer that spans a boundary isn't lost.