# What is the difference between an agent function and an agent program?

What is the difference between an agent function and an agent program (with respect to the percept sequence)?

In the book "Artificial Intelligence: A modern approach",

The agent function, notionally speaking, takes as input the entire percept sequence up to that point, whereas the agent program takes the current percept only.

Why does the agent program only take current percept. Isn't the agent program just an implementation of the agent function?