Language
Plain-language definitions for the terminology you'll encounter when building AI agents and LLM applications.
An autonomous AI system that perceives its environment, makes decisions, and takes actions to achieve goals — often using tools like web search, code execution, or APIs.
A technique that combines LLM generation with information retrieved from an external knowledge base, improving accuracy and reducing hallucinations.
A neural network trained on large text corpora that can generate, summarize, translate, and reason over text. Examples include GPT-4, Claude, and Gemini.
The coordination of multiple AI agents, tools, and processes to complete complex tasks. Orchestration manages sequencing, parallelism, and error handling.
A numerical representation of text, images, or other data as a point in high-dimensional space, enabling semantic similarity search.
A model that converts text, images, or other content into dense vector representations for use in similarity search and retrieval.
A capability that allows LLMs to call external functions or APIs — enabling agents to search the web, run code, read files, and interact with services.
A defined sequence of steps, decisions, and actions that automates a business process. In AACFlow, workflows connect AI models, tools, and data sources.
An event that starts a workflow automatically — such as a webhook, scheduled time, new email, database change, or API call.
A safety or compliance control applied to AI inputs or outputs — for example, filtering harmful content, validating structured output, or enforcing rate limits.
The process of measuring AI agent quality — comparing outputs to expected results, human feedback, or automated metrics to track performance over time.
The input text given to an LLM to elicit a desired response. Prompt engineering involves crafting effective prompts to guide model behavior.
Now that you know the terminology — try AACFlow free.