This course establishes the baseline vocabulary and review habits for the rest of the site. It treats AI systems as tools with tradeoffs rather than as magic, which makes later architecture and workflow guidance easier to absorb.
The first lesson explains why fluent output is not the same thing as verified truth. The second lesson adds the next operating habit: give the model the right source material and keep the relevant context close to the task. The verification lesson then shows learners how to spot hallucination patterns, choose review depth, and label confidence before using the result.
The final foundations habit is data-boundary discipline. Learners practice deciding what should not go into a prompt, upload, tool call, or shared AI output before they start using AI in real workflows.