# Free CAF practice questions

> 10 free CAF practice questions with the correct answer and an explanation.

Page: https://devopscodelab.com/exams/claude-associate-foundations/free-practice-questions/
Practice exams: https://devopscodelab.com/exams/claude-associate-foundations/

### Question 1 of 10

An HR specialist pastes a 12-page policy and a set of employee questions into one prompt. Claude sometimes treats lines from the policy as instructions. What is the BEST way to structure the prompt?

- A. Wrap the policy and the questions in separate XML tags and refer to those tags in the instructions
- B. Shorten the policy to a one-paragraph summary written from memory so there is less text to confuse Claude
- C. Put the instructions in capital letters so they stand out from the policy
- D. Split the policy into several separate messages and send the questions only after Claude confirms each part

**Answer:** A

**Explanation:** XML-style tags clearly separate reference material from instructions, and naming the tags in the instructions tells Claude exactly what to do with each part. Capital letters do not create a structural boundary. Sending many messages adds turns without delimiting content. A summary written from memory discards the source details the answers depend on.

### Question 2 of 10

A support lead plans to let Claude draft refund decisions. Drafts for refunds under $50 are low risk; larger refunds have caused costly mistakes. Which review design BEST balances speed and risk?

- A. Ask Claude to flag drafts it feels unsure about and send only those flagged drafts to a human reviewer
- B. Let Claude approve all refunds and audit a random sample of decisions at the end of each month
- C. Auto-approve low-value drafts after spot checks; route drafts above the threshold to a human
- D. Have a human review every draft regardless of value so that no decision is ever made without oversight

**Answer:** C

**Explanation:** A value-based threshold sends high-impact decisions to people while keeping low-risk work fast, which is the purpose of a human-in-the-loop threshold. Reviewing everything is safe but discards the efficiency gain. Monthly sampling finds costly mistakes too late. Model self-flagging is not a reliable trigger because confident output can still be wrong.

### Question 3 of 10

A policy team gives Claude three internal documents and asks for a summary that uses only those documents. Which instruction BEST supports checking that the summary is grounded?

- A. Ask Claude to add any helpful background it knows so the summary feels more complete
- B. Ask Claude to quote the supporting passage for each key claim
- C. Ask Claude to keep the summary under one page so there is less text to review
- D. Ask Claude to write in a neutral tone so the summary does not sound promotional

**Answer:** B

**Explanation:** Requiring a supporting quote for each claim lets reviewers trace every statement back to the provided documents and spot anything ungrounded. Adding outside background works against the only-these-documents requirement. Length and tone limits make review easier or nicer but do not show where claims come from.

### Question 4 of 10

An analyst needs a multi-source briefing on a competitor that draws on many web pages and internal Google Drive files, with citations. Which Claude capability is the BEST fit?

- A. Research, which searches the web and connected sources and returns a cited report
- B. A custom style called "Briefing" that makes Claude's responses longer and more formal
- C. Extended thinking with no sources attached, so Claude reasons more deeply from memory
- D. A single chat reply with web search off, using the knowledge Claude already has from training

**Answer:** A

**Explanation:** Research is designed to investigate a question across many searches, including connected sources such as Google Workspace, and produce a report with citations. Training knowledge alone is stale and uncited. A style changes presentation, not sources. Extended thinking without sources cannot retrieve current information.

### Question 5 of 10

A claims department classifies tasks as Automate, Augment, or Human-only. Which task belongs in Human-only?

- A. Sorting incoming emails into claim, complaint or general inquiry
- B. Making the final decision to deny a disputed claim
- C. Drafting a first summary of a claimant's submitted documents
- D. Translating a standard acknowledgment letter into Spanish

**Answer:** B

**Explanation:** A final denial of a disputed claim is a consequential, accountable decision that should rest with a person. Summarizing documents is augmentation with review. Translating a standard letter and sorting emails are good candidates for automation or light review.

### Question 6 of 10

A content team wants Claude to turn interview transcripts into blog posts. Results are inconsistent when they ask for everything in one prompt. Which workflow design BEST addresses this?

- A. Put all the steps into a single, much longer prompt with every rule written in capital letters
- B. Drop the transcripts and write from the topic alone
- C. Ask Claude to write five complete posts at once and let the team choose the best one each time
- D. Chain the work: extract quotes, then outline, then draft from the approved outline

**Answer:** D

**Explanation:** Prompt chaining breaks a complex task into steps whose outputs feed the next, and gives the team checkpoints to review. A longer single prompt keeps the same overloaded structure. Generating many full drafts wastes effort without fixing consistency. Removing the transcripts removes the source material the posts depend on.

### Question 7 of 10

A project's knowledge contains the 2024 and the 2026 versions of the same travel policy, and Claude sometimes quotes outdated limits. What is the BEST fix?

- A. Remove or archive the 2024 version so only the current policy remains
- B. Upload a third copy of the 2026 policy to outweigh the old one
- C. Rename the 2024 file with a longer name so that Claude reads it after the newer policy document
- D. Add an instruction asking Claude to pick whichever version it thinks is more likely to be correct

**Answer:** A

**Explanation:** Conflicting versions in project knowledge cause stale answers; curating the knowledge so only the current version is present removes the conflict at its source. Letting Claude guess keeps the risk. Duplicate copies and file renaming do not reliably stop the old policy being used.

### Question 8 of 10

An employee asks Claude to reproduce a full paywalled industry article so the team can avoid paying for a subscription. What is the MOST appropriate response under responsible use?

- A. Reproduce it, as long as the team removes the author's name afterward
- B. Do not reproduce it; summarize lawfully obtained material or buy access
- C. Reproduce it, provided the team keeps the text inside internal chats
- D. Reproduce it, because content generated by Claude is free of copyright

**Answer:** B

**Explanation:** Reproducing copyrighted articles in full to avoid paying infringes the publisher's rights; lawful options are summarizing material you have access to or licensing it. AI output of protected text does not remove copyright. Removing the byline or keeping it internal does not make the copy lawful.

### Question 9 of 10

A communications officer wants to paste an unreleased earnings announcement into Claude to polish the wording. What is the MOST appropriate action?

- A. Remove the company name but keep all figures, then paste it into a free personal account
- B. Paste it into any personal Claude account because the text will be public in a few days anyway
- C. Ask a colleague to paste it instead so the communications officer's account is not involved
- D. Use only an approved organization workspace and follow the company's MNPI rules

**Answer:** D

**Explanation:** Material non-public information must stay within approved tools and follow disclosure rules until it is released. Upcoming publication does not make early sharing acceptable. Removing the name leaves the sensitive figures. Using someone else's account does not change the policy breach.

### Question 10 of 10

In a long chat, a user corrected Claude's use of the wrong product name several times, but the error keeps returning. What is the BEST approach?

- A. Rename the product so it matches the name that Claude keeps using
- B. Start a fresh chat with the correct name stated clearly at the start
- C. Add more messages so the early wrong usage is pushed further back
- D. Keep correcting it in the same chat until Claude finally stops repeating the wrong name

**Answer:** B

**Explanation:** Early errors in a long conversation keep influencing later replies; a fresh chat with the correct term stated up front, or set in project instructions, removes the mixed signals. Repeated corrections keep both names in context. Renaming the product is not a fix. Adding messages grows the problem.

Ready for a timed run? Take the free 15-question CAF mini exam: https://devopscodelab.com/app/exams/claude-associate-foundations/mini/

DevOpsCode Lab is not affiliated with Anthropic. CAF and related names are trademarks of their owners. We write every question ourselves; these are not real exam questions.
