Unofficial Claude certification practice (szymonpaluch.com)

npx add-mcp 'https://szymonpaluch.com/mcp'

Unofficial practice material

Claude Certified Architect Foundations mock exam.

Take 60 original questions I wrote while studying for Claude Certified Architect Foundations. Choose study mode or a timed 120-minute attempt. Your results show which domains need more work, and this browser saves your progress so you can return later. The questions are in English. The test is free and needs no account.

Updated 10 October 2026

Three sample questions with answers and explanations →Foundations study plan →Preparing for CCAR-P: separate study guide →All four practice exams →Source on GitHub →Train your team on this →Practise inside Claude →

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

This mock uses single-answer questions across all six scenarios. The official CCAR-F also has multiple-response items and selects four of six scenarios. The mock uses its own scoring formula, with no validated correspondence to Anthropic’s exam score.

**

--:--

NO PARTNER EMPLOYER?

Anthropic admits to its exams only people from Claude Partner Network organizations. Join our collective of AI consultants and sit all four exams through our partner organization.

See the program →

Training a team? See the workshop

Your last attempt

0 —

Claude Certified Architect Foundations

Full Practice Exam · 60 Questions

60Questions

120 minTime limit

720 / 1000Mock threshold

4 optionsOne correct

Unofficial CCAR-F practice: 60 original single-answer questions across all six scenarios. The official exam also uses multiple-response items and selects four of six scenarios. The 120-minute limit helps you practise pacing; this tool does not reproduce the official exam or its scoring formula.

Choose a mode

Study mode Pick an answer, change your mind freely, then hit Check answer to reveal the explanation. The timer pauses while you read. Best for learning. Exam mode Timed practice: no feedback until you submit, and the timer runs the whole time. Practise pacing across 60 questions.

How this works

• Every question is multiple choice: one best answer, three plausible distractors.
• 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 D or 1 to 4 answer · ←/→ navigate · F flag.

Questions

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 Architect 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 Architect Foundations questions + a cheat sheet (12 rules, 7 traps)
• A practice question every weekday
• Access to all four Claude exams + an exam-day pack
• Client projects for certified members

See the program →

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 Architect Foundations exam guide.

About this mock exam

The CCAR-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 Architect Foundations exam guide (v1.0, July 2026).

• Questions

  60

• Question types

  One correct answer out of four

• Time limit

  120 minutes in exam mode

• Threshold

  720 out of 1000, a practice reference, not Anthropic’s scoring

Domains and weights

Domain	Weight in the exam guide	Questions in this mock
D1 Agentic Architecture & Orchestration	27%	16
D2 Tool Design & MCP Integration	18%	11
D3 Claude Code Configuration & Workflows	20%	12
D4 Prompt Engineering & Structured Output	20%	12
D5 Context Management & Reliability	15%	9

Three sample questions

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

Question 22 · D1 · Agentic Architecture & Orchestration

The synthesis subagent's reports read as generic overviews: in 30% of runs they omit the specific figures and named sources the web-search subagent surfaced. Tracing shows the Task prompt sent to the synthesis subagent contains only the report topic and formatting instructions. What is the best fix?

1. A. Increase the coordinator's context window so more findings stay resident across delegations
2. B. Have the coordinator embed the web-search and document-analysis findings verbatim in the synthesis subagent's Task prompt
3. C. Add a 'recall the earlier research' instruction to the synthesis subagent's system prompt
4. D. Give the synthesis subagent its own web-search tool so it can re-gather the missing figures

Show the answer

Correct answer: B. Subagents do not inherit the coordinator's conversation context; in a hub-and-spoke topology the coordinator must pass prior findings explicitly in the Task prompt, so embedding the web-search and document-analysis results verbatim is the fix. A larger context window (A) does not cross the process boundary into a freshly spawned subagent. Instructing it to 'recall' earlier research (C) fails because the subagent starts with no prior turns to recall. Giving it its own search tool (D) is wrong scope and over-engineering — it duplicates work and diverges from the evidence already gathered.

Question 31 · D2 · Tool Design & MCP Integration

The document-analysis subagent must call classify_document before running any field extraction, because the extraction schema depends on the detected type. Relying on a prompt instruction, it skips classification in 9% of runs and extracts against the wrong schema. The coordinator invokes it once per document, and the required first step is always the same. What is the best fix?

1. A. Set tool_choice to "any" so the subagent is required to use some tool on the opening turn
2. B. On the first turn, set tool_choice to the forced form {"type":"tool","name":"classify_document"} so classification always runs before extraction
3. C. Strengthen the system prompt with an emphatic "ALWAYS classify before extracting" plus two worked examples
4. D. Add an interception hook that inspects each extraction call and blocks it whenever no classification has run

Show the answer

Correct answer: B. When a specific tool must run first deterministically, forcing tool_choice to that named tool on the opening turn is the direct API mechanism and guarantees classify_document executes before any extraction. Setting tool_choice "any" (A) forces a tool but not which one, so the model could still call an extraction tool. A stronger prompt (C) is exactly the non-deterministic approach that already failed 9% of the time. An interception hook (D) would work but is heavier cross-tool policy machinery for a single fixed first-step ordering that the forced tool_choice already guarantees at the API level.

Question 11 · D3 · Claude Code Configuration & Workflows

Your team standardized naming and error-handling conventions by adding them to ~/.claude/CLAUDE.md on the tech lead's machine. Everything works for the lead, but three newly onboarded engineers who cloned the repo report that Claude Code ignores the conventions entirely, even though `git status` shows a clean checkout. What is the most effective fix?

1. A. Add an @import to the repo-root CLAUDE.md pointing at ~/.claude/CLAUDE.md so the personal file is pulled in for everyone
2. B. Have each engineer run /memory after cloning to force-reload the user-scoped memory files
3. C. Move the conventions into the project-scoped .claude/CLAUDE.md (or repo root) so they are committed to version control and load for every clone
4. D. Convert the conventions into a skill under .claude/skills/ so they activate on demand for all users

Show the answer

Correct answer: C. The CLAUDE.md hierarchy loads user-scoped instructions from ~/.claude/CLAUDE.md, which is personal to a machine and is NOT shared through version control — the classic 'new teammate didn't get the instructions' symptom. Committing the conventions to the project-scoped .claude/CLAUDE.md (or repo root) makes them load for every clone, so C is correct. An @import to ~/.claude/CLAUDE.md (A) fails because that file doesn't exist on the teammates' machines. Running /memory (B) only inspects already-loaded memory files; it cannot pull in instructions that were never in a shared scope. A skill (D) is on-demand rather than always-loaded, so it wouldn't provide the persistent conventions the team wants.

Frequently asked questions

Are these Anthropic’s CCAR-F exam questions?

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

What does the CCAR-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 CCAR-F domains weighted?

The exam guide weights the 5 domains as follows: Agentic Architecture & Orchestration 27%; Tool Design & MCP Integration 18%; Claude Code Configuration & Workflows 20%; Prompt Engineering & Structured Output 20%; Context Management & Reliability 15%. 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 CCA 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 CCA practice question from domain 2”, or pick the cca_practice_session prompt 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.

For a team lead

This test measures one person. A team is a separate question.

Want to train the team you write code with? The scope and prerequisites are below. Send this section’s link to the person who approves the budget.

• Who it is for

  Technical teams that write code every day. Up to 12 people in a group, so everyone gets time at an open laptop.

• What you need before the date

  We work in your repository. Before the workshop, describe your stack and goal, then check accounts and tool access on your company devices and network.

• Programme

  You work with code for two days: using agents on day one and building your own on day two, across six practical modules.

• Formats and prices

  Two days for a team of up to 12 cost from $4,800 online or $6,400 on-site, including travel. We agree the dates individually.

• What it is not

  It is not a preparation course for the Claude Certified Architect exam. This test and the explanations to all 60 questions are free and stay free. The workshop teaches production work, not exam technique.

See the full programme and the form →

Describe what you want to build with your team on the workshop page. I will reply to your enquiry.

Newsletter

The Agentic Architect

Practical patterns, case studies and AI news. Zero spam, once a week.

You'll get one email to confirm. Unsubscribe with one click. Privacy policy

Cookies

This site uses cookies and similar technologies to analyse traffic. Privacy policy