PromptForge
AI Glossary

Agents & tools

AI agent

Also known as: agents, agentic, ai agents

Definition

An AI agent is a system where a model plans and takes actions through tools in a loop, rather than producing a single response. It decides what to do next, does it, observes the result, and continues until the goal is met.

The distinguishing feature is the loop. A chatbot answers; an agent reasons about what it needs, calls a tool, reads the output, and reasons again. That loop is what lets it complete multi-step work like researching a topic across several sources or fixing a failing test.

Agents introduce failure modes that single prompts do not have. They can loop indefinitely, take costly wrong turns, and compound early mistakes across subsequent steps. Every production agent therefore needs explicit limits: a maximum number of steps, a budget, and a clear stopping condition.

The most reliable agents today are narrow. Broad autonomy remains unreliable; a well-scoped agent with three good tools and a clear success criterion works.

Related terms

ReAct pattern

ReAct (Reason + Act) is the core agent loop: the model reasons about what to do, takes an action via a tool, observes the result, then reasons again. It repeats until it can answer.

Function calling

Function calling lets a model request that your code run a specific function with specific arguments. You expose tool definitions; the model returns a structured call, your code executes it, and the result goes back into the conversation.

MCP (Model Context Protocol)

MCP is an open standard for connecting AI models to external tools and data sources. It replaces bespoke per-integration code with one protocol any compatible client can use.

Prompt chaining

Prompt chaining splits a complex task into a sequence of focused prompts, where each step's output feeds the next. Chains are easier to debug and more reliable than one large prompt.

Tool use

Tool use is a model invoking external capabilities — search, code execution, database queries, APIs — to do things it cannot do from parameters alone, such as fetching current data or performing exact arithmetic.

Guardrails

Guardrails are the constraints that keep an AI system inside acceptable behaviour — input validation, output filtering, topic restrictions, action limits and human approval gates.

Put this into practice

Understanding the term is step one. Our free courses and tools let you actually use it.

Browse courses Free toolsPrompt library

Topics

AI Agents

Related across the site

Prompt

Fact-Check This Claim

Verifying a statistic or claim before publishing. Run this on anything you did not source yourself, especially numbers pulled from a chat model — statistics are exactly the kind of detail models hallucinate confidently. Use a search-grounded tool so you get a live primary source and a date, and treat "no source found" as a reason to cut the claim rather than to keep looking.

Challenge

The Fabrication Hunt

Deliberately induce a confident, wrong answer, then find the prompt wording that prevents it. The most useful twenty minutes you can spend on calibrating how much to trust a model.

Article

What Are AI Agents? The Loop, the Limits, and the Hype

An AI agent plans and acts through tools in a loop rather than producing a single response. Here is how the ReAct pattern works, why agents fail, and what actually works in production today.

Glossary

Fine-tuning

Fine-tuning continues training a pre-trained model on your own examples to specialise its behaviour. It is the right tool for teaching consistent style, format or classification behaviour — not for adding knowledge.

Glossary

LoRA

LoRA (Low-Rank Adaptation) is a fine-tuning method that trains small adapter matrices instead of updating all model weights. It cuts the compute and storage cost of fine-tuning by orders of magnitude.

Glossary

Mixture of experts (MoE)

Mixture of experts is an architecture where only a subset of the model activates per token. A router selects a few specialised sub-networks, so a very large model runs at the cost of a much smaller one.