AI Basics

What machine intelligence is and how the pieces fit together.

AI Basics is taught here in 12 lessons, running from AI, machine learning, deep learning through to Designing an AI feature end to end. Each lesson takes one topic, shows the working code, and links onward to the next, so the course can be read straight through in order.

Lessons

1. AI, machine learning, deep learningThe three terms people use interchangeably, what a model actually is, and where the boundary of "intelligence" sits.
2. The model lifecycleFrom framing a problem to monitoring it in production — and why most AI projects fail before any model is trained.
3. Using a model APITokens, temperature, system prompts, structured output and cost control — the practical mechanics of calling an LLM.
4. Prompt engineering fundamentalsWrite instructions a model can follow: roles, few-shot examples, output constraints, and treating prompts as versioned artefacts rather than scratch text.
5. Embeddings and semantic searchTurn text into vectors, compare them with cosine similarity, chunk documents sensibly, and build a working search over your own corpus.
6. Retrieval-augmented generationGround answers in your own documents: index a corpus, retrieve the right passages, inject them as context, cite sources, and admit when nothing matches.
7. Choosing between prompting, RAG and fine-tuningCompare the three ways to change model behaviour by cost and effort, and know which problems fine-tuning genuinely solves.
8. Evaluating AI featuresBuild a test set with real inputs, score outputs offline, use a model as a judge with its biases in mind, and turn human review into a repeatable pipeline.
9. AI safety, privacy and data governanceDecide what data may leave your systems, handle prompt injection and unsafe output, and log enough to investigate an incident without creating one.
10. Local versus hosted modelsCompare hosted APIs with open-weight models you run yourself, size the hardware honestly, and route between the two when neither answer fits everywhere.
11. Multimodal AI in practiceSend images and documents to a vision model, transcribe and synthesise speech, and know where each modality still breaks down.
12. Designing an AI feature end to endTake a feature from specification to production: choose the model, ground it, evaluate it, guard it, monitor it, and plan the rollback before you ship.

More in AI & Intelligent Development

AI Agents Math for AI Machine Learning scikit-learn TensorFlow PyTorch Natural Language Processing LangChain Ollama OpenCV Codex Claude Code OpenCode Vibe Coding Selenium Playwright

FAQ