AI Concepts

Every concept on this site, grouped by category. Start wherever the actual gap is — there's no required order.

• AI Essentials — The basic building blocks worth understanding before the rest of this site's agent, tool, and retrieval concepts make full sense.
  Context Window · Fine-Tuning · Hallucination · LLM (Large Language Model) · Reasoning Models · Temperature · Token
• RAG — Retrieval-augmented generation grounds a model's answers in your own data at query time, instead of relying only on what it learned during training.
  RAG (Retrieval-Augmented Generation) · Embeddings · Chunking · Vector Database · Reranking · RAG Evaluation
• AI Agents — An AI agent decides its own next action instead of following a fixed script. What that means in practice, and what changes once more than one agent is involved.
  AI Agent · Agentic AI · Agentic Workflow · Multi-Agent System · Agent2Agent Protocol (A2A)
• AI Safety — The practical end of AI safety: how applications built on models actually get attacked, and how to limit the damage when something gets through.
  Guardrails · Human-in-the-Loop · Prompt Injection
• Prompting — How to actually instruct a model, what does and doesn't change the way it responds, and what belongs in its context at all.
  Few-Shot Prompting · Prompt Engineering · System Prompt
• Tools — The mechanisms that let a model do something — take an action, look something up — instead of only answering in text.
  Tool Calling · Function Calling · Structured Outputs
• AI Evaluation — How to tell whether an AI system is actually working, rather than just looking like it is, and how to keep telling once anything about it changes.
  AI Evals · LLM-as-Judge
• MCP — MCP standardizes how an AI application connects to external tools and data, instead of every pairing needing its own custom integration code.
  Model Context Protocol (MCP) · MCP Server
• Agent Skills — A skill packages instructions for one kind of task, kept out of an agent's prompt until that task actually comes up.
  Agent Skills
• Context Engineering — What information a model actually sees for a given task, and how to decide what belongs in there and what doesn't.
  Context Engineering
• Memory — What an AI system should deliberately remember between sessions, and what should stay temporary context instead.
  Agent Memory
• Production AI — Running AI systems for real, once actual users depend on them — cost, latency, monitoring, and what breaks at scale.
  Prompt Caching
• Subagents — A subagent is the same kind of system as an ordinary agent — the difference is who's calling it, and what that changes about how you'd design it.
  Subagent