Definitions for the terms you keep hearing. Written for founders, agency owners, and operators — not engineers. If we use jargon, we define it.
What is AI agent?
An AI agent is software that takes a goal, decides what steps to take, uses tools to do them, and carries the work out with little or no human prodding between steps.
Read the definition →
What is Agent builder?
An agent builder is a tool for creating AI agents — defining what they do, what tools they can use, and how they decide — without writing all the code yourself.
Read the definition →
What is MCP (Model Context Protocol)?
MCP — the Model Context Protocol — is an open standard that lets AI agents plug into tools, data sources, and apps the same way, so any agent can talk to any compliant tool.
Read the definition →
What is Agent marketplace?
An AI agent marketplace is a catalog where you can buy, install, or hire pre-built AI agents — like an app store, but for agents that work for you.
Read the definition →
What is Agentic workflow?
An agentic workflow is a process where AI agents make some of the decisions about what to do next — instead of just executing fixed steps you laid out in advance.
Read the definition →
What is Vertical AI agent?
A vertical AI agent is built and tuned for one industry — real estate, legal, accounting — so it knows the workflows, vocabulary, and tools of that field out of the box.
Read the definition →
What is Multi-agent system?
A multi-agent system uses several specialised AI agents that each handle part of a task, coordinated by an orchestrator — like a team rather than a soloist.
Read the definition →
What is RAG (retrieval-augmented generation)?
RAG — retrieval-augmented generation — is when an AI looks up relevant info from your documents before answering, so its replies are grounded in your actual content instead of just its training data.
Read the definition →
What is Tool calling?
Tool calling is when an AI agent decides to use a tool — like sending an email, looking up a record, or charging a card — instead of just talking about it.
Read the definition →
What is Agent orchestration?
Agent orchestration is the layer that decides which agent (or which step) handles which part of a task — coordinating multiple agents, tools, and humans toward an outcome.
Read the definition →
What is Agent memory?
Agent memory is what an AI agent remembers across messages or sessions — so it doesn't start from scratch every time you talk to it.
Read the definition →
What is Agent eval?
Agent eval is the practice of running an AI agent against test cases to measure whether it does the job correctly — so you can ship with confidence and catch regressions.
Read the definition →
We're extending the glossary as the space moves. If there's a term you keep running into and want a plain-English definition for, drop us a line at hello@squidgy.ai.
All this language exists because people are shipping. You can be one of them.