Learning roadmap

Work top to bottom. The primers build the muscles — prompting, embeddings and tool use — that every agentic technique depends on. Then the core track stacks those skills into full RAG and multi-agent architectures.

Foundations (primers)

  1. 1 01 · Prompt Playground beginner 15 min

    Discover how a prompt's structure — system persona, user request, and grounding context — shapes a model's output.
  2. 2 02 · Embeddings & Vector Search beginner 20 min

    Turn text into vectors and rank documents by cosine similarity — the retrieval engine behind every RAG system.
  3. 3 03 · Tool / Function Calling beginner 20 min

    Let the model decide when to call a tool, run it, and fold the result back into the answer — the loop that creates agents.

Core techniques

  1. 4 04 · Retrieval-Augmented Generation (RAG) intermediate 25 min

    Retrieve relevant context, then generate a grounded answer. The canonical pattern for trustworthy LLM answers.
  2. 5 05 · Agentic RAG intermediate 30 min

    Add a reasoning loop around retrieval: judge relevance, rewrite the query, and retrieve again before answering.
  3. 6 06 · Multi-Agent System advanced 30 min

    Split a task across specialised agents — researcher, analyst, writer — that hand off to one another.
  4. 7 07 · Agent Teams & Orchestration advanced 35 min

    A supervisor routes each task to the right specialised team, then reviews and merges the result.