Interactive Concept Map
Click any concept to explore its details and connections
Artificial Intelligence (AI)
The broad field of creating computer systems that can perform tasks requiring human-like intelligence.
Machine Learning (ML)
A subset of AI where computers learn from data rather than following explicit programming instructions.
Neural Network
A computational model with interconnected layers of nodes that process data to recognize patterns.
Deep Learning
Machine learning using neural networks with many layers to progressively learn complex patterns.
Model (AI Model)
A trained system that has learned patterns from data and can make predictions or generate outputs.
Large Language Model (LLM)
A deep learning model trained on vast text data to understand and generate human-like text.
Prompt
The input text or instructions you provide to an AI model to guide its response.
Prompt Engineering
The practice of crafting and refining prompts to consistently get high-quality outputs from AI models.
Token
The basic unit of text that language models process—typically a word, part of a word, or punctuation.
Context Window
The maximum amount of text a model can process in a single interaction, measured in tokens.
System Prompt / Instruction Hierarchy
A special prompt that defines the model's behavior, personality, and constraints throughout a conversation.
Temperature / Top-p (Sampling Parameters)
Settings that control the randomness and creativity of model outputs.
Training vs. Inference
Training is the learning phase where models learn from data; inference is using the trained model for responses.
Hallucination
When an AI model generates false or misleading information while appearing confident.
Retrieval-Augmented Generation (RAG) / Grounding
A technique that retrieves information from trusted sources before generating responses to improve accuracy.
Embeddings & Vector Databases
Converting text into numerical vectors that capture semantic meaning for similarity search.
Function / Tool Calling
The ability for language models to recognize when to use external tools and invoke them with proper parameters.
Model Context Protocol (MCP)
An open standard for connecting AI assistants to external data sources and tools in a consistent way.
AI Agents
AI systems that can autonomously perform tasks by breaking down goals, using tools, and making decisions.
Categories (click to toggle)
fundamentals
models
prompting
architecture
agents
Connections
Hierarchy
Flow
Relationship