CCAO-F Prompting and Context Engineering Practice Question
A support team is building a Claude-powered assistant that answers questions using a 200-page employee handbook. They place the entire handbook inside <handbook> tags in the system prompt and the user's question at the end of the user turn. Testing shows Claude sometimes ignores details buried in the middle of the handbook. Which change best addresses this while keeping the same model and context window?
⚠ Common exam trap
The trap here is assuming any tuning knob such as temperature or max_tokens can fix an attention/positioning problem that is really about where relevant content sits in the context.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Move the most relevant handbook sections to the beginning of the context, just before the user's question, and keep the full handbook available.
Long-context performance in Claude is not uniform: content near the beginning and end tends to be used more reliably than content buried in the middle. When a relevant section is stranded mid-document, retrieval degrades. Repositioning the most relevant excerpts adjacent to the question, while keeping the full handbook available, aligns the strongest signal with the query and fixes the observed symptom without changing model or window size.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Move the most relevant handbook sections to the beginning of the context, just before the user's question, and keep the full handbook available.
Why this is correct
Claude attends more reliably to information near the start and end of long contexts, a pattern often called 'lost in the middle.' Placing the most relevant sections adjacent to the question raises the chance the model uses them, while retaining the full handbook preserves coverage for follow-up questions. This directly targets the observed failure without changing the model or context window.
- ✗
Lower the temperature to 0 so Claude becomes deterministic and stops skipping handbook details.
Why it's wrong here
Temperature affects sampling randomness in generation, not the model's ability to retrieve facts from a long input. A deterministic setting can make outputs more consistent, but it will not make Claude attend to a section it is already underweighting in the middle of a 200-page context. The reported symptom is positional attention, so temperature is the wrong lever.
- ✗
Split the handbook into 200 separate user turns so each page gets equal attention from Claude.
Why it's wrong here
Flooding the conversation with 200 user turns consumes context, confuses turn structure, and still does not guarantee attention to each page. It also makes the interaction expensive and hard to maintain. The scenario needs better placement of relevant content, not artificial fragmentation of the source document into many turns.
- ✗
Increase the max_tokens parameter so Claude has more room to reason about the handbook before answering.
Why it's wrong here
max_tokens controls the length of Claude's generated output, not how much of the input context the model attends to. Raising it lets Claude write a longer answer but does nothing to fix attention drifting away from mid-context handbook content. The scenario's problem is input positioning, not output length, so this change leaves the root cause untouched.
About these practice questions
One of 259 original CCAO-F practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Anthropic exam blueprint
This CCAO-F practice question is part of Courseiva's free Anthropic certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the CCAO-F exam.