I want to understand
Fundamentals → LLMs → Glossary
Build an accurate mental model and a durable vocabulary.
Aura · AI learning path
A progressive, practical map of artificial intelligence—from machine learning and deep learning to tokens, Transformers, RAG, tools, agents, evaluation and safety. No magic words, no hype: concepts, decisions and checks you can reuse.
01 · Aura · AI learning path
Follow the order if you are starting out, or open the section that matches the problem you need to solve.
Separate systems, models and products; understand how learning differs from fixed rules.
Choose the right family of approach before choosing a model.
Open sectionTokens, embeddings, attention, Transformers, training, alignment and inference.
Reason about capabilities and limits without treating an LLM as a database.
Open sectionPrompt contracts, structured outputs, RAG, tools, MCP, agents and adaptation.
Match each technique to the failure it can actually address.
Open sectionBaselines, representative tests, factuality, injection, privacy, cost and rollout.
Decide with measured evidence and limit the system’s blast radius.
Open sectionSearch 46 essential terms, from algorithm and gradient to RAG and quantization.
Decode technical discussions and documentation quickly.
Open sectionTurn an objective, context and success criteria into a portable AI instruction.
Produce a clear prompt you can inspect, edit and reuse.
Open section02 · Aura · AI learning path
Most useful LLM systems are pipelines. Quality depends on the weakest interface, not only on the model.
Define the user need, risk and observable success.
Provide relevant context, data or retrieval.
Use the model with explicit constraints and format.
Authorize tools narrowly and validate every boundary.
Measure quality, safety, cost and failure recovery.
03 · Aura · AI learning path
Core principle: a fluent answer is a proposal, not proof. Keep important claims traceable and important actions bounded.
Fundamentals → LLMs → Glossary
Build an accurate mental model and a durable vocabulary.
LLMs → Skills → Evaluation
Design a useful system and test it against real cases.
Fundamentals → Builder → Evaluation
Give clearer instructions and review outputs critically.