Sintra AI
Home
Live Feed
Automation Hub
Prompt Library256
AI News554
Weekly Digest
Topic Hubs
AI History
AI Labs
Research
Learning Paths
Guides
Resources
Concepts
Videos
AI Tools74
Models
Claude
Google AI
Cost Calc
librAIry
54 concepts

Concepts & Definitions

AI, decoded.

Plain-English definitions for every AI term you’ll encounter — from tokens to agents, APIs to MCP.

🧠

Machine Learning

Fundamentals·Beginner·17 May 2025

Teaching computers to learn from examples, not rules.

LLMFine-tuningEmbeddings
🪙

Tokens

Fundamentals·Beginner·17 May 2025

The tiny chunks of text an AI reads, one at a time.

Context WindowLLM
✨

Prompt Engineering

Fundamentals·Beginner·17 May 2025

The art of asking AI the right question in the right way.

LLMTool UseAI Agents
⬡

Large Language Model

LLM
Models & AI·Practitioner·17 May 2025

AI trained on vast text to understand and generate language.

TokensContext WindowPrompt Engineering
🪟

Context Window

Models & AI·Beginner·17 May 2025

How much text an AI can see and remember at once.

TokensLLMRAG
🗺️

Embeddings

Models & AI·Technical·17 May 2025

Turning words and ideas into numbers that capture meaning.

RAGMachine LearningLLM
📚

Retrieval-Augmented Generation

RAG
Models & AI·Practitioner·17 May 2025

Giving the AI access to your documents before it answers.

EmbeddingsContext WindowLLM
🎯

Fine-tuning

Models & AI·Technical·17 May 2025

Specialising a general AI model on your specific data and style.

Machine LearningLLMPrompt Engineering
⚡

AI Agents

Tools & Agents·Practitioner·17 May 2025

AI that plans and takes actions without you guiding every step.

LLMTool UseSkills
🧩

Skills

Tools & Agents·Practitioner·17 May 2025

Pre-built capabilities you attach to an AI to extend what it can do.

AI AgentsConnectorsTool Use
↔️

Connectors

Tools & Agents·Practitioner·17 May 2025

Bridges that let AI read from and write to your apps and services.

MCPAPIAI Agents
🔌

API

API
Protocols·Beginner·17 May 2025

A standardised way for software to talk to other software.

MCPTool UseConnectors
🔗

Model Context Protocol

MCP
Protocols·Technical·17 May 2025

A universal standard for AI to connect to any tool or data source.

APIConnectorsTool Use
🛠️

Function Calling

Tool Use
Protocols·Practitioner·17 May 2025

Letting an AI invoke real code and APIs mid-reasoning.

AI AgentsAPIMCP
🔓

Open Source LLMs

Models & AI·Practitioner·23 May 2026

Frontier-quality AI models anyone can download, run, and modify.

LLMFine-tuningRunning Models Locally
💻

Running Models Locally

Tools & Agents·Practitioner·23 May 2026

How to run AI on your own machine — private, free, and offline.

Open Source LLMsFine-tuningLLM
⚡

Jevons Paradox

Fundamentals·Practitioner·24 May 2026

Making AI cheaper creates more usage, not less.

TokensAI AgentsAmplifier
📣

AI as Amplifier

Amplifier
Fundamentals·Beginner·24 May 2026

AI multiplies what you already are — good or chaotic.

Software EcologyJevons ParadoxAI Agents
🌿

Software Ecology

Fundamentals·Practitioner·24 May 2026

The holistic study of social and technical systems that produce software.

AmplifierJevons ParadoxAI Agents
🌡️

Temperature

temp
Models & AI·Beginner·30 May 2026

The dial that controls how random or predictable an AI's output is.

LLMTokensPrompt Engineering
👁️

Hallucination

Fundamentals·Beginner·30 May 2026

When an AI generates confident-sounding facts that are simply wrong.

LLMRAGPrompt Engineering
📋

System Prompt

Fundamentals·Beginner·30 May 2026

The hidden instruction that shapes how an AI behaves before you say anything.

Prompt EngineeringLLMTool Use
🔗

Chain of Thought

CoT
Fundamentals·Practitioner·30 May 2026

Prompting a model to reason step-by-step before giving its final answer.

Prompt EngineeringLLMtemp
🎨

Multimodal AI

Models & AI·Beginner·30 May 2026

AI that understands and generates more than one type of media — text, images, audio, or video.

LLMTool UseAI Agents
🗄️

Vector Database

Tools & Agents·Practitioner·30 May 2026

A database that stores meaning, not just text — finding similar content by concept rather than keyword.

EmbeddingsRAGAPI
⚡

Inference

Models & AI·Practitioner·30 May 2026

The moment a trained model actually runs and generates output.

LLMTokensFine-tuning
📊

AI Benchmark

Models & AI·Practitioner·30 May 2026

Standardised tests that measure what a model can actually do.

LLMFine-tuningInference
🛡️

AI Safety

Fundamentals·Practitioner·30 May 2026

The field working to ensure AI systems do what humans actually want — now and as they become more capable.

Prompt EngineeringAI AgentsLLM
⚙️

Transformer

Models & AI·Technical·3 Jun 2026

The architecture that made modern AI possible — attention over sequences.

LLMAttention MechanismEmbeddings
👁️

Attention Mechanism

Models & AI·Technical·3 Jun 2026

How a model decides which words to focus on when understanding a sentence.

TransformerLLMContext Window
🎛️

Mixture of Experts

MoE
Models & AI·Technical·3 Jun 2026

A model architecture that activates only a fraction of its parameters per request.

LLMTransformerInference
🎓

Reinforcement Learning from Human Feedback

RLHF
Models & AI·Technical·3 Jun 2026

Training AI to be helpful and safe by learning from human preference ratings.

Fine-tuningCAILLM
📜

Constitutional AI

CAI
Models & AI·Technical·3 Jun 2026

Teaching AI to critique and revise its own outputs against a written set of principles.

RLHFAI SafetyLLM
🗜️

Quantization

Models & AI·Technical·3 Jun 2026

Compressing a model's weights to use less memory and run faster — with minimal quality loss.

Running Models LocallyOpen Source LLMsFine-tuning
🎨

Diffusion Model

Models & AI·Technical·3 Jun 2026

The AI behind image generation: learning to reverse the process of adding noise.

Multimodal AILLMEmbeddings
🧮

Reasoning Model

Models & AI·Practitioner·3 Jun 2026

AI that thinks through a problem step by step before giving its final answer.

CoTLLMAI Benchmark
🎯

Few-Shot Prompting

Fundamentals·Beginner·3 Jun 2026

Giving an AI 2–5 examples of the task before asking it to do yours.

Prompt EngineeringCoTLLM
⚡

Zero-Shot Prompting

Fundamentals·Beginner·3 Jun 2026

Asking an AI to do a task with no examples — just instructions.

Few-Shot PromptingPrompt EngineeringCoT
📅

Knowledge Cutoff

Fundamentals·Beginner·3 Jun 2026

The date after which an AI model has no training data — and doesn't know what happened.

LLMRAGHallucination
⚓

Grounding

Fundamentals·Practitioner·3 Jun 2026

Connecting an AI's response to real, verifiable sources rather than memory alone.

RAGHallucinationKnowledge Cutoff
💉

Prompt Injection

Fundamentals·Practitioner·3 Jun 2026

A security attack where malicious instructions hidden in content hijack an AI agent.

AI AgentsAI SafetySystem Prompt
⚡

Prompt Caching

Protocols·Practitioner·3 Jun 2026

Reusing the processed version of a repeated prompt prefix to cut cost and latency.

APITokensInference
📐

Structured Output

Protocols·Practitioner·3 Jun 2026

Forcing an AI to respond in valid JSON or a specific schema — every time.

APITool UseAI Agents
🌊

Streaming

Protocols·Beginner·3 Jun 2026

Receiving an AI's response token by token as it's generated, not all at once.

APIInferenceTokens
🤖

AI Agents

Tools & Agents·Practitioner·23 Jun 2026

An AI that plans, takes actions through tools, and adapts based on what it observes.

Tool UseMulti-Agent SystemsAI Memory
🔧

Function Calling / Tool Use

Tool Use
Tools & Agents·Practitioner·23 Jun 2026

How a model triggers real code — a search, a database query, a calculation — instead of just generating text.

AI AgentsMulti-Agent SystemsPrompt Injection
🖥️

Computer Use

Tools & Agents·Practitioner·3 Jun 2026

AI that can see a screen and control a computer — mouse, keyboard, and all.

AI AgentsTool UseMultimodal AI
🕸️

Multi-Agent Systems

Tools & Agents·Technical·3 Jun 2026

Multiple AI agents working together, each handling a specialised role in a larger workflow.

AI AgentsTool Use
🧠

AI Memory

Tools & Agents·Practitioner·3 Jun 2026

How AI agents store and retrieve information across turns, sessions, and tasks.

AI AgentsRAGVector Database
🔄

Agent-to-Agent Protocol

A2A
Protocols·Technical·3 Jun 2026

A standard for AI agents from different systems to communicate and delegate tasks to each other.

MCPAI AgentsMulti-Agent Systems
🎯

Red-Teaming

Fundamentals·Practitioner·3 Jun 2026

Adversarial testing of AI systems to find failure modes before deployment.

AI SafetyPrompt InjectionLLM
📄

Model Card

Models & AI·Beginner·3 Jun 2026

A standardised document describing what an AI model can do, how it was built, and where it falls short.

AI SafetyAI BenchmarkLLM
⚖️

Direct Preference Optimisation

DPO
Models & AI·Technical·3 Jun 2026

A simpler alternative to RLHF that trains models on human preferences without a reward model.

RLHFFine-tuningCAI
📦

Context Compression

Models & AI·Practitioner·3 Jun 2026

Techniques to fit more useful information into a limited context window.

RAGContext WindowTokens
⬡

Add a concept

Every concept follows a fixed schema in src/lib/concepts.ts. Add an entry to the CONCEPTS array with: id, term, category, tagline, body, analogy, icon, difficulty, related.