CAF
Claude Architect Foundations (CAF) practice exams
290 questions in 5 timed practice tests. Each test has about 60 questions and a 120-minute limit. The pass mark is 72%. Results are split across the 5 exam domains.
Exam at a glance
| Practice tests | 5 |
|---|---|
| Questions in total | 290 |
| Questions per test | About 60 |
| Time limit per test | 120 minutes |
| Pass mark | 72% |
| Question types | Single answer and multiple answer (29 multiple-answer questions) |
| Level | Professional |
| Category | AI & Machine Learning |
These are the settings of our practice tests. Check the official Anthropic exam page for the current exam format before you book.
Domains and weights
| Domain | Weight | Weight bar | Questions in our bank |
|---|---|---|---|
| Agentic Architecture & Orchestration | 27% | 78 | |
| Tool Design & MCP Integration | 18% | 52 | |
| Claude Code Configuration & Workflows | 20% | 58 | |
| Prompt Engineering & Structured Output | 20% | 58 | |
| Context Management & Reliability | 15% | 44 |
Sample questions
Question 1 of 3, choose 2
A team is designing the delegation prompt a coordinator sends to a web-research subagent. Which TWO elements most improve the quality and usability of the subagent's result? (Choose two.)
- A The coordinator's complete raw conversation history so the subagent can infer what is needed
- B An instruction to keep searching until it has exhausted every possible source on the topic
- C A clear objective with scope boundaries, such as which sources and time range are in or out (correct answer)
- D A request that the subagent rewrite the coordinator's system prompt to better suit its own task
- E An explicit output format, for example a list of findings each with its source URL and publication date (correct answer)
Question 2 of 3
A coordinator agent must research five independent sub-topics, and total latency matters. Each sub-topic is handled by the same research subagent definition. How should the coordinator dispatch the work to minimise wall-clock time?
- A Invoke one subagent at a time and pass each result into the next call so later subagents can build on earlier findings
- B Emit all five subagent invocations as separate tool calls in a single assistant response so they run in parallel (correct answer)
- C Give a single subagent all five topics in one prompt and instruct it to interleave the searches as efficiently as possible
- D Start five separate coordinator sessions with the same system prompt and merge their final answers in application code
Question 3 of 3
A research system spawns ten subagents for every query, including simple factual questions like 'What year was the company founded?' Costs are high and simple answers are slow. What is the BEST adjustment?
- A Route all simple questions to a smaller model while keeping ten subagents for every incoming query
- B Have the coordinator scale effort to complexity: one agent for simple facts, more subagents for broad research (correct answer)
- C Cache every subagent result for 24 hours so that repeated questions can skip the multi-agent run entirely
- D Lower the subagent count to five for all queries so the cost of every request falls by roughly half
See all 10 free CAF questions with answers Read them or quiz yourself.
What your score report looks like
Example attempt, CAF practice test 3
78%
Passed
Pass mark 72%
| Domain | Weight | Your score | % |
|---|---|---|---|
| Agentic Architecture & Orchestration | 27% | 88 | |
| Tool Design & MCP Integration | 18% | 81 | |
| Claude Code Configuration & Workflows | 20% | 76 | |
| Prompt Engineering & Structured Output | 20% | 58 | |
| Context Management & Reliability | 15% | 84 |
Study next: Prompt Engineering & Structured Output. It is below the pass mark and carries 20% of the exam.
Study plans
Two weeks
- Day 1: take practice test 1 in exam mode to get a baseline.
- Days 2 to 5: domain mode on Agentic Architecture & Orchestration and Claude Code Configuration & Workflows, the two most heavily weighted domains.
- Day 6: practice test 2 in exam mode, then the mistakes quiz.
- Days 7 to 12: practice tests 3 to 5, one every other day, each followed by its mistakes quiz.
- Days 13 and 14: final mode. Book the exam when your readiness stays above the pass mark.
Four weeks
- Week 1: one practice test in practice mode, reading every explanation. Note your two lowest domains.
- Week 2: domain mode on those two domains, then a second practice test in exam mode.
- Week 3: practice tests 3 and 4 in exam mode, with the mistakes and flagged quizzes after each.
- Week 4: practice test 5 and final mode until your readiness holds above the pass mark.
Questions about the CAF practice exams
- Are these real CAF exam questions?
- No. We write every question ourselves and map it to the published CAF exam objectives. We do not use leaked or recalled questions.
- Do the time limit and pass mark match the official exam?
- They match the settings of our practice tests. Exam providers change their format from time to time, so check the official exam page before you book.
- Can I try it before I pay?
- Yes. The free mini exam has 15 questions with full explanations and needs no account.
- How long do I keep access?
- A single-exam purchase gives you 12 months of access. All-Access includes this exam for as long as your subscription runs.
- What happens after I finish a test?
- You get a score, a pass or fail against the pass mark, a score per domain and every answer with its explanation.
Related exams
| Exam | Vendor | Level | Questions | Minutes | Price |
|---|---|---|---|---|---|
| CCDV-FClaude Developer - Foundations (CCDV-F) | Anthropic | Associate | 300 | 120 | $12.99 |
| CAFClaude Associate Foundations | Anthropic | Associate | 300 | 120 | $12.99 |
| 1Z0-1122-26OCI AI Foundations 1Z0-1122-26 | Oracle | Foundational | 300 | 90 | $9.99 |
| AB-731AI Transformation Leader AB-731 | Microsoft | Foundational | 250 | 100 | $9.99 |
| AB-900Copilot & Agent Admin AB-900 | Microsoft | Foundational | 225 | 45 | $9.99 |
| AI-901Azure AI Fundamentals AI-901 | Microsoft | Foundational | 225 | 45 | $9.99 |