AI & Prompting Glossary

Clear, plain-language definitions of the AI and prompting terms used across LearnPrompt — from “prompt” and “token” to “agent”, “MCP”, and “prompt injection”. Use the search box to find a term, or link straight to any definition.

46 terms

Agentic workflow
A task designed to run largely on its own through an agent's plan-act-observe loop, set up with a clear goal, the tools it may use, and guardrails on what it may do.See also: AI agent, Guardrails
AI agent
A system that takes a goal and works toward it on its own -- planning steps, using tools, and checking results in a loop -- instead of just answering a single prompt.See also: Agentic workflow, Tool use, MCP (Model Context Protocol), Prompt chaining
API
Application Programming Interface -- a way for software to talk to an AI model directly in code rather than through a chat window, used to build AI into apps and automate prompts.
Chain-of-thought
A prompting technique that asks the model to reason step by step before answering, which improves results on problems that need logic or several steps.See also: Prompt engineering, Reasoning model
Chatbot
A conversational AI tool you use by typing messages back and forth, such as ChatGPT, Claude, or Gemini.See also: Large language model (LLM)
Context engineering
The practice of shaping everything a model can see when it answers -- documents, data, history, and tools -- not just the wording of the prompt.See also: Context window, Prompt engineering, RAG (Retrieval-Augmented Generation)
Context window
The amount of text a model can hold in view at once, measured in tokens. Everything it uses to answer -- your prompt, pasted documents, and the conversation so far -- must fit inside it.See also: Token, Context engineering
Custom instructions
Saved preferences that tell a chatbot how to respond to you every time, so you do not have to repeat them in each new chat.See also: System prompt
Delimiter
A clear marker -- such as triple quotes or tags -- used to separate your instructions from pasted content, helping the model treat that content as data and reducing prompt injection.See also: Prompt injection, Prompt engineering
Embedding
A numeric representation of text that captures its meaning, letting software find passages with similar meaning. The basis of retrieval and vector search.See also: Vector database, RAG (Retrieval-Augmented Generation), Retrieval
Few-shot prompting
Giving the model a few examples of the input and the output you want before your real request, so it follows the pattern.See also: Zero-shot prompting, Prompt engineering
Fine-tuning
Further training a base model on extra examples so it specializes in a task or style. Unlike prompting, it changes the model itself, not just the input.See also: Training data, Large language model (LLM)
Frontier model
One of the most capable, cutting-edge AI models available at a given time.See also: Large language model (LLM)
Function calling
A capability that lets a model trigger a defined function or tool with structured inputs, so it can take actions or fetch data instead of only producing text.See also: Tool use, MCP (Model Context Protocol)
Generative AI
AI that creates new content -- text, images, audio, or code -- by predicting likely outputs, rather than only classifying or retrieving existing data.See also: Large language model (LLM)
Grounding
Tying a model's answer to real, supplied facts (documents or data) rather than its general memory, which reduces made-up information.See also: RAG (Retrieval-Augmented Generation), Retrieval, Hallucination
Guardrails
Rules and limits placed around a model to keep its behavior safe and on-topic -- what it must refuse, must not reveal, or must get approval for.See also: Prompt injection, Jailbreaking, System prompt
Hallucination
When a model states something false or invented as if it were true, because it generated a plausible-sounding continuation rather than a verified fact.See also: Grounding
Inference
Running a trained model to produce an output from an input. "Inference" means using a model, as opposed to training it.See also: Latency, Temperature
Jailbreaking
Crafting input that gets a model to bypass its own safety rules and do something it would normally refuse.See also: Prompt injection, Guardrails
Knowledge cutoff
The date after which a model has no built-in knowledge, because its training data ends there. Newer events require web search or context you provide.See also: Training data, Hallucination
Large language model (LLM)
An AI model trained on huge amounts of text to predict likely next words, which lets it answer questions, write, summarize, and more. The engine behind chatbots.See also: Generative AI, Token, Parameter
Latency
The delay between sending a prompt and getting a response back from a model.See also: Inference
MCP (Model Context Protocol)
An open standard that lets any AI app connect to external tools and data sources in a uniform way -- often called the "USB-C" of AI tools.See also: Tool use, Function calling, AI agent
Multi-agent orchestration
A setup where several specialized agents handle different parts of a task, coordinated by an orchestrator that passes work between them.See also: AI agent, Agentic workflow
Multimodal
Able to work with more than one type of input or output -- for example text together with images, audio, or video.
Open-weight model
A model whose trained weights are publicly released, so anyone can run, inspect, or adapt it. Often called open-source, though licenses vary.See also: Large language model (LLM), Fine-tuning
Parameter
One of the many internal values a model learns during training. Models are often described by their parameter count (for example, billions), a rough proxy for capacity. (Not to be confused with a fill-in placeholder in a prompt.)See also: Large language model (LLM), Fine-tuning
Persona prompting
Telling the model to take on a role or expertise ("act as a copy editor") to shape the tone and focus of its answer. Also called role prompting.See also: Prompt engineering, System prompt
Prompt
The input you give an AI model -- your question, instruction, and any context -- that it responds to.See also: Prompt engineering, Prompt template
Prompt chaining
Breaking a task into a sequence of prompts where each step's output feeds the next, instead of asking for everything at once.See also: AI agent, Prompt engineering
Prompt engineering
The skill of writing clear, well-structured prompts to get reliable, useful results from an AI model.See also: Context engineering, Few-shot prompting, Prompt template
Prompt injection
When instructions hidden inside content a model is processing -- an email, a web page, a file -- get the model to act against the user's intent.See also: Jailbreaking, Guardrails, Delimiter
Prompt template
A reusable prompt with [bracketed placeholders] you fill in each time, so you get consistent results without rewriting it.See also: Prompt engineering, Prompt
RAG (Retrieval-Augmented Generation)
A technique that fetches relevant passages from your own documents and adds them to the prompt, so the model answers from real sources.See also: Retrieval, Grounding, Embedding
Reasoning model
A model designed to work through problems in more steps before answering, trading some speed for stronger performance on complex tasks.See also: Chain-of-thought
Retrieval
Searching a collection of documents for the passages most relevant to a question, usually to feed them into a prompt.See also: RAG (Retrieval-Augmented Generation), Vector database, Embedding
Structured output
Output produced in a specified format -- such as JSON, a table, or a bulleted list -- so it can be used reliably by a person or another program.See also: Prompt engineering
System prompt
Background instructions that set a model's role, rules, and behavior for a whole conversation, separate from each user message.See also: Persona prompting, Guardrails, Custom instructions
Temperature
A setting that controls how random a model's output is. Lower is more focused and predictable; higher is more varied and creative.See also: Inference
Token
The unit of text a model reads and generates -- roughly three-quarters of a word. Usage and context limits are measured in tokens.See also: Context window, Large language model (LLM)
Tool use
A model's ability to call external tools -- search, code execution, file access, app connections -- to get real results instead of guessing.See also: Function calling, MCP (Model Context Protocol), AI agent
Training data
The large body of text and other content a model learns its patterns from during training.See also: Fine-tuning, Knowledge cutoff
Vector database
A store of embeddings that lets software quickly find text with similar meaning -- the lookup engine behind retrieval and RAG.See also: Embedding, Retrieval, RAG (Retrieval-Augmented Generation)
Vibe coding
Building software mostly by describing what you want in natural language and letting an AI generate the code, reviewing and steering rather than writing it line by line.See also: AI agent, Tool use
Zero-shot prompting
Asking a model to do a task with no examples, relying on what it already learned during training.See also: Few-shot prompting