Courses

Building AI Applications

Put a model behind a product: the request and its parameters, structured outputs and function calling, retrieval, and the cost, latency and privacy decisions that ship.

Islands
4
Lessons
25
Exercises
143
DebugCode orderFill blankMultiple choiceTapTrace

Start the first lesson

  1. Island 1

    Models and the API

    The request an application actually sends: messages and roles, the parameters that change the answer, the token budget that sets the bill, and the errors a production client must survive.

    1. The Request5 exercises, 5 min
    2. Parameters That Change the Answer5 exercises, 5 min
    3. Tokens, Budget and Cost5 exercises, 6 min
    4. Errors, Rate Limits and Retries5 exercises, 5 min
    5. Images and Documents as Input5 exercises, 6 min
    6. Checkpoint: The RequestCheckpoint7 exercises, 6 min
    7. Boss: The First EndpointBoss8 exercises, 9 min
  2. Island 2

    Structured Outputs and Function Calling

    Get a shape back instead of prose, run the tool loop from the application's side, handle results and errors without losing the thread, and validate everything before it touches your data.

    1. Asking for a Shape5 exercises, 5 min
    2. The Tool Loop From the App Side5 exercises, 6 min
    3. Results, Errors and Parallel Calls5 exercises, 5 min
    4. Validate, Then Repair5 exercises, 5 min
    5. Checkpoint: Shapes and ToolsCheckpoint6 exercises, 6 min
    6. Boss: The Support Triage BotBoss8 exercises, 9 min
  3. Island 3

    Retrieval and Context

    Give the model the right few pages instead of the whole library: when to retrieve, how chunks and embeddings work, how to assemble a context the model can cite, and how to tell when retrieval is the wrong tool.

    1. Why Retrieve5 exercises, 5 min
    2. Chunks and Embeddings5 exercises, 6 min
    3. Assembling the Context5 exercises, 6 min
    4. Checkpoint: The Right PageCheckpoint6 exercises, 6 min
    5. Boss: The Docs AssistantBoss8 exercises, 9 min
  4. Island 4

    Cost, Latency and Shipping

    The decisions between a demo and a product: which model for which request, caching, streaming and latency, what may enter a prompt and a log, and the checks that run before and after launch.

    1. Routing and Caching5 exercises, 5 min
    2. Streaming and Latency5 exercises, 5 min
    3. The Stream on the Wire5 exercises, 6 min
    4. What May Enter a Prompt5 exercises, 5 min
    5. Before and After Launch5 exercises, 5 min
    6. Checkpoint: ProductionCheckpoint7 exercises, 6 min
    7. Boss: Launch WeekBoss8 exercises, 9 min