The AI Encyclopedia

27 AI terms in plain language, for professionals who are not engineers or researchers.

Each entry gives a one-sentence definition, the key takeaways, how the idea works, a business example and the most common mistake. Read one entry in two minutes.

Core ideas

  • Artificial Intelligence (AI)Artificial intelligence (AI) is software that does tasks that normally need human thinking, such as reading, writing, planning and recognizing images.
  • Context WindowA context window is the maximum amount of text, measured in tokens, that an AI model can read and consider at one time.
  • Generative AIGenerative AI is AI that creates new content, such as text, images, audio, video or code, in answer to a request written in plain language.
  • InferenceInference is the moment a trained AI model does its job. It takes your input and produces an output.
  • Large Language Model (LLM)A large language model (LLM) is an AI system trained on a very large amount of text. It reads and writes language by predicting which words come next.
  • Machine Learning (ML)Machine learning (ML) is the method behind modern AI. A program learns to do a task from many examples, with no person writing the rules by hand.
  • TokenA token is the small unit of text that an AI model reads and writes. A token is often a short word or a part of a longer word.
  • Training DataTraining data is the collection of examples, such as text, images or audio, that an AI model learns from before anyone uses it.

Working with models

  • EmbeddingAn embedding is a list of numbers that represents the meaning of a piece of text, so that software can compare texts by meaning and not only by exact words.
  • Fine-TuningFine-tuning is extra training that adapts an existing AI model to a specific task or style, with a smaller set of examples.
  • Multimodal AIMultimodal AI is AI that works with more than one kind of content, such as text, images, audio and video, in the same conversation.
  • PromptA prompt is the instruction you give an AI model. It can be a question, a task, a document with a request, or all of these together.
  • Prompt EngineeringPrompt engineering is the practice of writing and testing instructions for an AI model so that it gives reliable, useful output.
  • Reasoning ModelA reasoning model is an AI model that works through a problem in steps before it gives its final answer.
  • Retrieval-Augmented Generation (RAG)Retrieval-augmented generation (RAG) is a method in which an AI tool first finds relevant passages in your documents and then writes its answer from those passages.
  • System PromptA system prompt is a set of standing instructions that an AI tool gives the model before your conversation starts. It sets the role, the rules and the tone.
  • TemperatureTemperature is a setting that controls how much variety an AI model puts in its answers. A low value gives steady, predictable output. A high value gives more varied output.

Agents and automation

  • Agent SkillAn agent skill is a saved package of instructions, and sometimes files and scripts, that teaches an AI agent how to do one specific kind of task your way.
  • Agentic WorkflowAn agentic workflow is a business process in which one or more AI agents do a sequence of steps, with fixed checkpoints and limits set by a person.
  • AI AgentAn AI agent is an AI system that works toward a goal across many steps. It decides what to do next, uses tools such as search, files and apps, and checks its own progress.
  • AI LoopAn AI loop is a setup in which an AI agent repeats a cycle of work, check and improve until the result passes a test you defined.
  • Model Context Protocol (MCP)The Model Context Protocol (MCP) is an open standard that lets AI tools connect to outside apps and data, such as your calendar, your files or your CRM, in one common way.

Quality and safety

  • Evaluation (Evals)An evaluation, or eval, is a repeatable test that measures how well an AI model, prompt or agent does a specific task.
  • GuardrailsGuardrails are the rules and checks that keep an AI system inside safe and approved limits, such as blocked topics, required formats and actions that need approval.
  • HallucinationA hallucination is an AI answer that sounds confident and correct but is false or invented, such as a made-up quote, number, source or event.
  • Human in the LoopHuman in the loop means that a person reviews, corrects or approves the work of an AI system at set points before the work has an effect.
  • Prompt InjectionPrompt injection is an attack in which text hidden in a web page, an email or a document tricks an AI system into following the attacker's instructions and not yours.

More reference pages

Last updated . AI agents can read the full text of all entries at /llms-full.txt.