AiDex · Learn
Learn AI Tools
Everything you need to understand and use AI tools effectively — from essential vocabulary to advanced techniques. Start with the basics or dive into specific tool categories.
LLM
Large Language Model — an AI system trained on massive text datasets to understand and generate human language. Examples: GPT-4, Claude, Gemini.
Prompt
The input you give to an AI model. Better prompts lead to better outputs. Prompt engineering is the skill of crafting effective prompts.
Context Window
The amount of text an AI can consider at once, measured in tokens. Larger context windows allow longer conversations and documents.
Token
The basic unit AI models use to process text. Roughly 4 characters or 0.75 words. APIs charge per token.
Hallucination
When an AI generates false information presented as fact. Common with specific names, dates, URLs, and citations.
Fine-tuning
Training an existing model on custom data to specialize it for specific tasks or domains.
RAG
Retrieval-Augmented Generation — connecting an AI to external data sources so it can answer questions about your documents.
Embedding
A numerical representation of text that captures its meaning. Used for semantic search and similarity matching.
Temperature
A setting that controls randomness in AI outputs. Lower = more consistent, higher = more creative.
System Prompt
Instructions that define how an AI should behave throughout a conversation. Sets the persona, rules, and boundaries.
Zero-shot
Asking an AI to perform a task without providing examples. "Write a haiku about AI."
Few-shot
Providing examples in your prompt to guide the AI output format or style.
Chain-of-thought
Prompting technique where you ask the AI to explain its reasoning step-by-step, improving accuracy on complex tasks.
Multimodal
AI systems that can process multiple input types — text, images, audio, video — in a single interaction.
Agent
An AI system that can take actions autonomously — browsing the web, running code, or using tools to complete tasks.
MCP
Model Context Protocol — an open standard for connecting AI assistants to external data sources and tools.
Inference
When an AI processes your input and generates an output. What happens when you press "send" on a chat.
Latency
The delay between sending a prompt and receiving a response. Smaller, faster models have lower latency.
API
Application Programming Interface — how developers connect their software to AI services like OpenAI, Anthropic, or Google.
Guardrails
Safety measures that prevent AI from generating harmful, biased, or inappropriate content.
Agentic
AI behavior involving autonomous decision-making, tool use, and multi-step task completion without human intervention.
Skills
Reusable prompt templates or tool configurations that extend what an AI assistant can do.
Tool Use
When an AI calls external functions or APIs to retrieve data, perform calculations, or take actions.
Grounding
Techniques to connect AI responses to factual sources, reducing hallucinations and improving accuracy.