WEEK 6 · LESSON 7 · TOPIC 1 OF 13 · Core Idea

Core Idea

Lesson progress

0% Complete

SECTION 1 OF 1

In this topic · 1 sections
  1. Overview

Overview

An agent can improve a system autonomously when three conditions exist:

  1. A metric to optimize.
  2. A direct way to change the system that influences the metric.
  3. A repeatable assessment that measures the result after each change.

When these conditions are present, the work can be organized as an experimental loop: form a hypothesis, make one change, measure the result, keep improvements, discard regressions, record the outcome, and repeat.