AI Builder
Build AI features and apps
AI Builder is a free course for developers who want to build AI features into real apps. It covers calling model APIs, writing prompts in code, retrieval-augmented generation (RAG), embeddings and vector search, simple agents, and how to test whether your AI feature actually works.
What you'll learn
- Call a model API and handle its answers in code
- Ground answers in your own documents with RAG
- Use embeddings and vector search to find relevant text
- Build a simple tool-using agent, and know its limits
- Write evals so you know when a change makes things worse
Who this course is for
- Developers adding AI to an app
- Students building AI projects for their portfolio
- Product people who want to understand how AI features are built
Inside the first unit
Call a model from code, make answers cite their evidence, and manage what the model sees.
- Your first API call
- Make answers cite evidence
- Context windows in apps
- Keep API keys on the server, never in front-end code.
- A model can only ground an answer in the evidence it receives.
- Every call is fresh: your app decides what fits in the context window.
After the first unit, Pli keeps going: new units are written for your level and goals as you learn, and every question is checked by a second AI before you see it.
Key terms in this course
Questions about AI Builder
What do I need to know first?
Basic programming helps. If you're new to AI itself, start with AI Foundations or Use AI Well.
Does it cover RAG?
Yes. Retrieval-augmented generation is a core topic: how to retrieve the right text and make the model cite it.
Is it free?
Yes, AI Builder is a free core course.
Free, five minutes a day. No sign-up needed to try your first lesson.
Updated 18 October 2026