---
title: "Context window & tokens — CCAR-P 2.4 practice questions"
description: "5 CCAR-P practice questions on objective 2.4: Optimize context windows and manage token usage. Part of domain 2, Models, Prompting & Context Engineering."
url: "https://claudearchitectguide.com/drill/obj/2-4"
image: "https://claudearchitectguide.com/og.png"
---

Objective 2.4 · Domain 2 · 13% of the exam

# Optimize context windows and manage token usage

Context-window management: what to put in, what to leave out, and what to do when the material exceeds the budget. Summarisation, truncation strategy and ordering effects all appear here, as does the fact that a full context window is not a free one. Cost and latency both scale with it, and recall over very long contexts is not uniform. A stem that says "we are passing the entire document set" is usually pointing at retrieval instead.

5 questions · answers and explanations shown as you go · free, no sign-up

## The rest of domain 2: Models, Prompting & Context Engineering

This domain is 13% of a scored form, about 8 of the 63 questions, spread across 5 objectives. [Drill the whole domain](https://claudearchitectguide.com/drill/2) or pick another objective below.

- [2.1 Select appropriate Claude models based on trade-offs (6)](https://claudearchitectguide.com/drill/obj/2-1)
- [2.2 Design system prompts, templates, and guardrails (5)](https://claudearchitectguide.com/drill/obj/2-2)
- [2.3 Apply prompt engineering techniques (zero-shot, few-shot, chain-of-thought)(5)](https://claudearchitectguide.com/drill/obj/2-3)
- [2.5 Implement prompt reuse strategies (caching, modular prompts, Skills)(5)](https://claudearchitectguide.com/drill/obj/2-5)

One objective is a narrow slice. A full-length timed mock is what tells you whether the whole thing holds together.

[Sit a timed mock →](https://claudearchitectguide.com/exam)
