Glossary

AI agent

A system that uses a language model to plan and take multi-step actions, such as calling tools or APIs, toward a goal.

Also called: LLM agent, autonomous agent

An AI agent is a system built around a large language model that does not just answer a single prompt but plans and executes a sequence of actions, calling external tools, running queries, browsing data, or invoking APIs, to work toward a goal, often deciding for itself what step to take next based on the results of the previous one.

This differs from a simple prompt-response interaction or an AI copilot, which typically assists a human working step by step; an agent is given more autonomy and can loop through observe-plan-act cycles with limited or no human input between steps. Agents rely heavily on prompt engineering to define their available tools and constraints, and often use retrieval-augmented generation to look up information mid-task.

Agents matter in analytics because they can automate multi-step work, such as investigating an anomaly, pulling data, and drafting a summary, that previously required a person to orchestrate manually; this use case is sometimes called agentic analytics. The central risk is compounding error: a wrong step early in a chain can lead the agent further off course, which is why production agents are typically wrapped in guardrails and given narrow, well-defined permissions.

Last reviewed September 22, 2026

In the index now

Related terms

Large language model (LLM) A neural network trained on vast amounts of text to predict and generate language, the technology behind most modern AI assistants. Prompt engineering Designing and refining the instructions given to a language model to reliably get the output you want. Guardrails Rules, filters, or checks placed around a language model to keep its inputs and outputs within acceptable, safe bounds. AI copilot An AI tool embedded in a work application that assists a human with suggestions or drafts, rather than working unsupervised. Agentic analytics The use of AI agents that autonomously plan and execute multi-step analytics work, such as investigating a metric change. Retrieval-augmented generation (RAG) An architecture that retrieves relevant documents at query time and feeds them to a language model so its answers are grounded in sources.

Related guides

How to use AI for data analysis safely Text-to-SQL and AI data assistants can speed up analysis or produce fluent wrong answers — the difference is what sits between the model and your data.