Unofficial practice material

Claude Certified Associate Foundations practice exam.

Take 60 original questions written from Anthropic’s published Associate – Foundations exam guide and weighted by its seven domains: prompting, checking output, choosing products and models, workflows, Projects and connectors, governance and troubleshooting. There is no code. Some questions ask you to select more than one answer, as the real exam does. Choose study mode or a timed 120-minute attempt. Your results show which domains need more work, and this browser saves your progress. The questions are in English. The test is free and needs no account.

Updated

Unofficial practice material. This test is not authorized or endorsed by Anthropic. The original questions are based on the publicly available Claude Certified Associate – Foundations exam guide.

Like the official CCAO-F, this mock mixes single-answer and multiple-response questions; a multiple-response question scores only when every pick is right. The mock uses its own scoring formula, with no validated correspondence to Anthropic’s exam score.

--:--
Your last attempt
0 —

Claude Certified Associate Foundations

Full Practice Exam · 60 Questions

60Questions
120 minTime limit
720 / 1000Mock threshold
Mixed1 or more correct
Unofficial CCAO-F practice: 60 original questions across all 7 domains, weighted like the official exam guide. 9 of them are multiple response: the question says how many answers to select, and it scores only when every pick is right. The 120-minute limit helps you practise pacing; this tool does not reproduce the official exam or its scoring formula.
Choose a mode
How this works
  • Most questions have one best answer. 9 ask you to select two or three; the question says how many, and it scores only when every pick is right.
  • Navigate freely, flag questions for review, and jump around with the question palette.
  • In study mode nothing is revealed until you press Check answer. Until then you can switch options freely; after checking, the question locks. In exam mode you can change answers until you submit.
  • Answer every item. Unanswered questions are scored as incorrect (as on the real exam).
  • Submit to get this mock’s score (100 to 1000, threshold ≥ 720), a per-domain breakdown, and full explanations.
  • Your progress autosaves in this browser. Shortcuts: A to F or 1 to 6 answer · ←/→ navigate · F flag.
0scaled score
—

—

Your next step

Anthropic registers only people from Claude Partner Network companies. No partner employer? The Certified AI Consultant Program, a collective for consultants who build with AI, registers you through our partner organisation. The certificate is Anthropic’s, the same one partner employees earn.

The pass mark is 720. In the Certified AI Consultant Program you prepare with others and register for the real exam through our partner organisation.

Retake guarantee. Score 720+ here in exam mode and send the result from the email address you pay with: fail the real Associate exam as a member and your next 2 months are free.

  • Access to all four Claude exams + an exam-day pack
  • A full-length practice set for each of the four exams
  • A practice question every weekday
  • Client projects for certified members
  • A full-length set of 60 extra Associate questions + a cheat sheet (12 rules, 8 traps)
  • A practice question every weekday
  • Access to all four Claude exams + an exam-day pack
  • Client projects for certified members

See the program →

One email from contact@szymonpaluch.com. Privacy policy

Performance by domain

Review & explanations

Certified AI Consultant Program

Next: the real exam. Members sit all four Claude exams through our partner organisation.

Prepare with the prep packs, then sit the exam through our partner organisation.

See the program →

This mock uses its own formula: 100 + 900 × (correct ÷ total). Its 720 threshold is a practice reference, not Anthropic’s scoring method or a validated prediction of your official result.

Unofficial practice material. This test is not authorized or endorsed by Anthropic. The original questions are based on the publicly available Claude Certified Associate – Foundations exam guide.

About this mock exam

The CCAO-F mock exam: format, domains and sample questions

The questions in this section come from the same bank as the test above. The domain weights are from Anthropic’s Claude Certified Associate Foundations exam guide (v1.0, July 2026).

Questions
60
Question types
51 single-answer and 9 multiple-response questions
Time limit
120 minutes in exam mode
Threshold
720 out of 1000, a practice reference, not Anthropic’s scoring

Domains and weights

DomainWeight in the exam guideQuestions in this mock
D1 Prompting and Task Execution14%8
D2 Output Evaluation and Validation21%13
D3 Product and Model Selection12%7
D4 Workflow Integration and Solution Design16%10
D5 Configuration and Knowledge Management12%7
D6 Governance, Risk, and Responsible Use15%9
D7 Troubleshooting and Optimization10%6

Three sample questions

Pick an answer before you open the explanation. Every question in the test above works the same way.

Question 30 · D2 · Output Evaluation and Validation

A marketing manager asked Claude for talking points on customer-loyalty trends, and Claude answered from its own knowledge without searching the web. One point quotes a named analyst at a well-known research firm, with a report title and year. She searched the firm's website and the wider web and found neither the analyst nor the quote. The deck goes to a client tomorrow. What should she do?

  1. A. Ask Claude for the report's web address, and keep the quote if the link opens a page on the research firm's website
  2. B. Keep the point but soften the attribution to "as one analyst reportedly said", which avoids naming a specific person
  3. C. Ask Claude whether the quote is genuine, and keep it in the deck if Claude confirms the wording and the report title
  4. D. Treat the quote as a likely fabrication and leave it out unless she can find it in the original report herself
Show the answer

Correct answer: D. D is right: a specific quote that cannot be found anywhere fits a known hallucination pattern, and Claude's help center warns that Claude can display quotes that look authoritative but are not grounded in fact. Only the original report can confirm it. A treats a page that opens as proof, but a working link does not show that the quote appears on that page. B keeps words that may be invented and only blurs who supposedly said them. C asks the same model to vouch for its own output, which is not independent evidence.

Question 28 · D4 · Workflow Integration and Solution Design

A business analyst has notes from 14 stakeholder interviews about a new expense-approval process. Finance wants every claim approved within 48 hours, regional managers want to approve small amounts themselves, and internal audit needs a full approval trail. The steering group will sign off a requirements list next week. How should she use Claude to analyze the requirements?

  1. A. Ask Claude for the requirements of a typical expense-approval process from its general knowledge, attaching the notes as background
  2. B. Have Claude settle conflicting requests by keeping whatever most interviewees asked for, so the list goes to sign-off with no open issues
  3. C. Ask Claude for a polished requirements document first, and check it against the notes only if a stakeholder raises an objection
  4. D. Have Claude list each requirement with its stakeholder and quote, merge duplicates, and flag conflicts and gaps for her to resolve
Show the answer

Correct answer: D. D is right: tying each requirement to a stakeholder and a direct quote keeps the list grounded in what people actually said and makes it auditable, and flagging conflicts such as delegated approval versus a full audit trail leaves the trade-offs for people to decide. A fails because generic requirements describe a typical process, not this organization's needs. B fails because a majority vote is not a priority rule; audit's single requirement may be mandatory, and hiding conflicts misleads the steering group. C fails because checking only when someone objects lets omissions and invented requirements reach sign-off.

Question 23 · D2 · Output Evaluation and Validation

An operations coordinator used Claude for five outputs this week. Which TWO need checking by a qualified person or independent verification before they are used?

  1. A. Five subject-line ideas for the internal staff newsletter, from which the newsletter editor will choose one
  2. B. A summary of a new data-retention law that will set how long the company keeps its customer records
  3. C. A tidier version of her own meeting notes, which she uses only as her personal to-do list for the week
  4. D. A first-draft agenda for next week's team meeting, which she will adjust as the discussion goes along
  5. E. Import duty amounts Claude calculated from 40 supplier invoices, to be entered on a customs declaration
Show the answer

Correct answer: B and E. B and E are right: B is a legal interpretation that will drive a compliance decision, so someone qualified, such as the legal or privacy lead, should confirm it, and E is a calculation for an official filing, which the help center says should be verified with specialized software or by hand. The help center also warns against relying on Claude as a single source of truth for high-stakes advice. A is a set of options the editor screens anyway. C is for her own use and easy to correct. D is a draft she will change during the meeting. In these three, normal use already catches errors at low cost.

Frequently asked questions

Are these Anthropic’s CCAO-F exam questions?

No. This is an independent mock exam with 60 original questions written from Anthropic’s public Claude Certified Associate Foundations exam guide. It is not affiliated with or endorsed by Anthropic, and no question is taken from the exam itself.

What does the CCAO-F exam look like?

Anthropic’s exam guide (v1.0, July 2026) lists 60 multiple-choice and multiple-response questions, a 120-minute time limit and a pass at a scaled score of 720 on a 100 to 1,000 scale.

How are the CCAO-F domains weighted?

The exam guide weights the 7 domains as follows: Prompting and Task Execution 14%; Output Evaluation and Validation 21%; Product and Model Selection 12%; Workflow Integration and Solution Design 16%; Configuration and Knowledge Management 12%; Governance, Risk, and Responsible Use 15%; Troubleshooting and Optimization 10%. The questions in this mock belong to the same domains, so your results show where to study.

How is the mock scored?

The score is 100 + 900 × the share of correct answers, and 720 is the threshold. The formula is mine, not Anthropic’s, so the result is a practice reference and does not predict your exam score.

Do I need an account or an email address?

No. The test is free and runs in your browser, which saves your progress so you can come back later. Your score and every explanation appear without an email address.

MCP server

Practise CCAO-F inside Claude

Add szymonpaluch.com as a connector in Claude to work through the same 60 questions in chat. You get one question at a time. Pick your answer, then see the correct choice and its explanation. No signup or API key is required.

Server URL
https://szymonpaluch.com/mcp
Claude (web and desktop)
Customize → Connectors → + → Add custom connector, then paste the URL above. The Free plan allows one custom connector.
Claude Code
claude mcp add --transport http szymonpaluch https://szymonpaluch.com/mcp
Then ask
“Give me a CCAO-F practice question from domain 2”, or pick the cca_practice_session prompt and name CCAO-F for a full round with a score at the end.

Questions are in English. The same server can also search and read this blog, list my services, prices and talks, and give you the booking link. It works with any MCP client that supports remote (Streamable HTTP) servers.