# Lab: AI Fundamentals for Developers Get hands-on with the four core pillars of AI application development: models, prompt engineering, tool calling, and RAG. This lab runs entirely on your machine using Docker Model Runner — no API key or cloud account required. ## Launch the lab

  1. Start the labspace:

    $ docker compose -p labspace -f oci://dockersamples/labspace-ai-fundamentals up -d
    Note

    This lab uses an AI model, which requires the Docker Model Runner to be enabled. The model may take some time to download.

  2. Open your browser to http://localhost:3030.

  3. When you're done, tear down the labspace:

    $ docker compose -p labspace down
## What you'll learn By the end of this Labspace, you will have completed the following: - Understand the Chat Completions API and how to structure messages for a model - Use prompt engineering techniques including system prompts, few-shot examples, and structured output - Implement tool calling and the agentic loop in code - Build a RAG pipeline that grounds model responses in your own data ## Modules | # | Module | Description | | --- | ------------------------------------ | ----------------------------------------------------------------- | | 1 | Welcome & Setup | Introduction to the lab and verifying your environment | | 2 | Talking to Models | Chat Completions API, message roles, and stateless model behavior | | 3 | Prompt Engineering | System prompts, few-shot examples, and structured output | | 4 | Tool Calling | Tool definitions, the agentic loop, and executing tools in code | | 5 | Retrieval Augmented Generation (RAG) | Retrieve, augment, and generate with your own knowledge base | | 6 | Wrap-up | Summary of concepts and next steps |