AI Foundations

Understand how modern AI works and build useful AI-powered applications.

Start with the engineering.

  1. Understand
  2. Inspect
  3. Build
  4. Verify
01 / Core concept

Treat a model response as a proposal, not evidence. Context limits bound what a model can inspect.

02 / Engineering practice

Define an output schema before prompting; validate required fields outside the model.

03 / Test the boundary

Check answers against source data and evaluate failure cases as well as successful ones.

This starter track connects published foundational lessons and guided browser workshops. Extended Python, API, retrieval, and deployment curriculum retains its existing publication status.

  • Language models
  • Prompt design
  • Tokens & context
  • Structured outputs
  • Model limitations
  • Verification & evaluation
All learning tracks