All videosOther topics0:36

Context engineering versus prompt engineering

Quality depends on which evidence, state, and tools enter each turn, not only on prompt wording.

Links containing ?t= open the video at a specific second.

Video summary

The ideas to retain

01

First, what does “context” mean here?

The word context is overloaded. In this chapter, it means the effective input available to one specific inference.

02

Prompt engineering is one part of the problem

Prompt engineering still matters. Ambiguous, contradictory, or excessively prescriptive instructions can degrade behavior even when the rest of the system is sound.

03

Context is a snapshot, not the full application state

This distinction prevents a particularly dangerous mistake in agent systems: treating “the system knows X” as equivalent to “the model can use X now.”

Key moments

Jump directly to a section

  1. Fixed prompt versus live context
  2. Per-turn selection and assembly
  3. Context changes after observation