Two Pipelines, Zero Trust: Building SkillSprint AI

Automated excerpt

Concretely, that means two independent pipelines that share no logic: • Pipeline 1 (generative) turns source documents into lessons, tasks and quiz questions using Gemini - or, if no API key is configured, a deterministic rule-based generator that produces structurally identical output from the same documents. • Pipeline 2 (rule-based) never touches the model. This does two things at once: it constrains what the model can even return (only plain types survive Gemini's schema subset, so every semantic rule still must be enforced afterward in code), and it means our application code never touches raw model text.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.