---
title: "Prompt engineering technique — CCAR-P 2.3 practice questions"
description: "5 CCAR-P practice questions on objective 2.3: Prompt engineering technique. Part of domain 2, Models, Prompting & Context Engineering."
url: "https://claudearchitectguide.com/drill/obj/2-3"
image: "https://claudearchitectguide.com/og.png"
---

Objective 2.3 · Domain 2 · 13% of the exam

# Apply prompt engineering techniques (zero-shot, few-shot, chain-of-thought)

Zero-shot, few-shot and chain-of-thought, and knowing which the situation calls for. Few-shot earns its tokens when the task has an idiosyncratic format or an edge case that a description cannot convey. Chain-of-thought earns its latency when the task has genuine intermediate reasoning. Applying either reflexively is the error being tested, and you should expect stems where the right answer is a clearer instruction instead of more examples.

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)
- [2.4 Optimize context windows and manage token usage (5)](https://claudearchitectguide.com/drill/obj/2-4)
- [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)
