---
title: "RAG chunking & indexing — CCAR-P 3.5 practice questions"
description: "5 CCAR-P practice questions on objective 3.5: Design a RAG pipeline with appropriate chunking and indexing strategies. Part of domain 3, Integration."
url: "https://claudearchitectguide.com/drill/obj/3-5"
image: "https://claudearchitectguide.com/og.png"
---

Objective 3.5 · Domain 3 · 19% of the exam

# Design a RAG pipeline with appropriate chunking and indexing strategies

Designing a retrieval-augmented generation pipeline: chunking, embedding, indexing, and the choices inside each. Chunk size trades recall against precision. Overlap protects meaning that straddles a boundary. Structure-aware splitting beats fixed-length splitting on documents that have structure. The most common wrong answer is a larger chunk size offered as a fix for poor retrieval quality, when the real problem is chunking that ignores the document's structure.

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

## The rest of domain 3: Integration

This domain is 19% of a scored form, about 12 of the 63 questions, spread across 8 objectives. [Drill the whole domain](https://claudearchitectguide.com/drill/3) or pick another objective below.

- [3.1 Evaluate tool/agent configuration for capability bloat (5)](https://claudearchitectguide.com/drill/obj/3-1)
- [3.2 Analyze authentication and authorization requirements to identify security gaps (5)](https://claudearchitectguide.com/drill/obj/3-2)
- [3.3 Evaluate accuracy-latency trade-offs and justify configuration decisions (5)](https://claudearchitectguide.com/drill/obj/3-3)
- [3.4 Analyze observability challenges and select monitoring strategies at scale (5)](https://claudearchitectguide.com/drill/obj/3-4)
- [3.6 Apply retrieval strategies matched to data shape and query pattern (5)](https://claudearchitectguide.com/drill/obj/3-6)
- [3.7 Evaluate connection protocols and select the appropriate integration mechanism (MCP, API/CLI, agent-to-agent)(4)](https://claudearchitectguide.com/drill/obj/3-7)
- [3.8 Evaluate progressive discovery vs. monolithic context strategy (4)](https://claudearchitectguide.com/drill/obj/3-8)

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)
