Understand AI.
One concept at a time.
From your first “what is AI?” to building intelligent systems. Clear explanations, real examples, and one familiar world to connect it all.
Welcome to the Sky Research Library.
Imagine a library that learns to help its visitors. Data is its collection. A model is its trained librarian. A prompt is your request. We’ll return to this same world as the ideas get more advanced.
Meet the rest of the library
Analogies build intuition; the technical definitions explain where the comparison stops. Models do not need human awareness or intentions to perform these operations.
Read in order, or jump to what you’re curious about.
The big picture
Understand what AI is, where machine learning fits, and what a model actually does.
Think of the whole Sky Research Library: the people, rules, catalog, and tools working together to help visitors. AI is the entire idea of an intelligent service.
Where it’s used
Search, route planning, assistants, image recognition, and decision support.
A concrete example
A library assistant identifies a question about astronomy, finds relevant books, and drafts a response. Several different AI techniques may support those steps.
How it works
- 1Define a task and what success means.
- 2Choose rules, learned models, search, or a combination.
- 3Evaluate results in the setting where the system will be used.
Intelligent-looking output is not evidence of consciousness, understanding like a human, or factual correctness.
Data & mathematical intuition
The raw materials, representations, and mathematical ideas behind learning.
How machines learn
Learning paradigms, the training loop, and the balance between memorizing and generalizing.
Classical machine learning
Practical models for tables, groups, patterns, and forecasts.
Evaluate before you trust
Understand errors, choose meaningful metrics, and test on truly unseen data.
Inside neural networks
From one artificial neuron to networks that recognize, remember, and generate.
Language & transformers
How text becomes numbers, how attention works, and how language models generate.
Prompting & reasoning
Turn requests into clear instructions, useful context, and verifiable outputs.
RAG & knowledge retrieval
Connect generation to your documents, and learn what makes retrieval reliable.
Adapt & align models
When to train, when to retrieve, and how to adapt models efficiently.
Agents & tool use
Build systems that can work through a task while keeping control of their actions.
MCP, plugins & skills
Understand the protocol, build a small server, and package capabilities clearly.
Perception & reinforcement learning
See, hear, and learn through action and feedback.
From prototype to production
Deploy, monitor, and operate an AI system as part of a real product.
Safety, trust & responsible AI
Look beyond average accuracy to security, privacy, fairness, and accountability.
Advanced architectures & frontiers
Efficiency, scale, and emerging approaches—without treating research as settled fact.
Built on good references.
Original explanations, examples, and library analogies, informed by primary research, official documentation, and public course outlines. Start with these learning paths, or follow the source links inside each concept.
Google Machine Learning Crash Course
Foundations, learning objectives, and curriculum structure.
Explore the course 02 / LEARNING PATHHugging Face LLM Course
NLP, transformers, and language-model foundations.
Explore the course 03 / LEARNING PATHEd Donner: AI Engineer Core Track
Public curriculum inspiration: models, RAG, adaptation, and agents.
Explore the courseBrowse all 67 references
Content reviewed September 20, 2026. AI is a growing field; this guide covers core concepts and selected advanced techniques, rather than claiming a complete vocabulary. APIs and implementation details evolve—check the linked documentation for your installed version.
Independent educational guide. Not affiliated with the referenced course creators or organizations.