Skip to content

GlossaryOften confused

LLMorAgent

A language model is a part: you call it, it produces text, and there it stops. An agent is the system that calls that part in a loop, carries out what it proposes and calls it again with the result, until the goal is reached.

Point by point

A comparison of LLM and Agent, criterion by criterion.
CriterionFloor 1Floor 1 · The Modela solid block on its own: the prediction machineLLMFloor 3Floor 3 · The Agentthe block caught in a loop: it starts again until it gets thereAgent
What is being namedA part: a model you callA system that calls that part in a loop
What comes outText, nothing elseActions, and their effects
What stops itThe end of its answerThe goal reached, or a limit you set
Calls to the modelOneOne per turn, as many as it takes
Cost of a unit of workKnown: the tokens in and outUnknown in advance: it depends on the number of turns
What can go wrongA false sentenceAn act performed in the world, sometimes irreversible

On the ground four situations

  • In a processing chain, one step sends a paragraph to the model and gets a category back.

    Floor 1 · The Modela solid block on its own: the prediction machineLLMOne call, one output, done: that is the whole extent of what a model does. What comes before and after is code someone wrote.

  • Taking over a codebase: read the files, attempt a change, run the tests, read the error, start again until everything passes.

    Floor 3 · The Agentthe block caught in a loop: it starts again until it gets thereAgentThe model is called at every turn, but what drives the task is the loop around it: the loop is what calls again, with the result of the previous turn.

  • A model returns an action plan in ten numbered steps, precise and convincing.

    Floor 1 · The Modela solid block on its own: the prediction machineLLMThe useful counter-example: describing steps is not carrying them out. As long as nobody reads that plan in order to run it, there is only text.

  • A conversation interface that answers, keeps your preferences and can open a document you point it at.

    AssistantNeither one: the model alone keeps nothing and opens nothing, and nothing here loops towards a goal. Everything described belongs to the harness, and the product is called an assistant.

The test that settles it

Take a task and count the calls to the model in the execution trace. A single call: you were looking at a model, and all the rest is code written around it. A series of calls, each starting from the result of the previous one: that is an agent.

The trap

“The AI decided to refuse the application.” The sentence points at the model and blames the wrong party: a model decides nothing on its own, it produces text when called, then it stops. What decides is the system that chose to execute that text rather than put it to someone.

Check click your answer

Level 1 · Recognise

You call a language model, and you do nothing more. What happens next?

Level 2 · Distinguish

An agent works for half an hour on a task. How many times was the model called?

Level 2 · Distinguish

Two products call exactly the same model: one returns an answer and stops, the other carries a task through by chaining dozens of steps. Where does the gap come from?

v2026-08 · a frontier observed, not inventedCite this page
Report

What goes with your message

Frontier · LLM or Agent
v2026-08 · /en/vs/llm-agent

What is this about
0 / 600

It is used to reply to you, and for nothing else. What is recorded