Running the agent

You have an agent, a tool and a model. Runner is the thing that puts them together and keeps going until there is an answer.

One trip round the loop

You ask. Runner.run takes the agent and your question.Step 1 of 4

Putting the three together

python

support = Agent(
    name="Support",
    instructions="Answer using the tools you have. Be brief.",
    model=PretendModel(),
    tools=[lookup_order],
)

This is the first time an agent has been given a model and a tool. Nothing has run yet, it is still a description.

python

result = await Runner.run(support, "Where is order A17?")

One line, and everything happens inside it. Runner.run is asynchronous, which is why there is an await, and the panel can run that directly.

Read the three items

The output ends with a list of what happened, and it is worth reading slowly.

Item	What it was
`ToolCallItem`	The model asking for `lookup_order`. Not an answer, a request.
`ToolCallOutputItem`	Your function's return value, put back into the conversation.
`MessageOutputItem`	The model again, this time with words, having seen the tool's answer.

Those three items are the agent loop. Every framework you read about is that shape with more comfort on top, and once it makes sense, agents make sense.

Break it on purpose

Take tools=[lookup_order] out and run it again. The model has nothing to ask for, so you get one item instead of three, and the answer comes straight from the model.

Try it yourself

Remove the tool and count the items.
Ask something without A17 in it and see which rule the model follows.
Print result.final_output only, and nothing else.

PreviousA model you can run for free

This is what real progress feels like.