Claude Certified Architect – Foundations (CCA-F) exam prep
Free study guide, practice questions and mock exams for Anthropic's Claude Certified Architect – Foundations exam (CCA-F, now also coded CCAR-F). Everything you need, on one page. Bookmark this page. Every lesson, mind map, trap and mock exam is linked from here. The exam tests judgement: each question gives you several sensible options, and you pick the one that fits the situation best.
- The exam in one minute
- Your study path
- Scenarios × domains
- The five domains
- Mind maps
- Trap gym: all 30 traps
- Mock exams
- Reference pages
1 The exam in one minute
Most wrong answers are good practices used in the wrong place. Three families cover most of them:
2 Your study path
- Learn the five domains, biggest first (section 4). Each has lessons, diagrams and a quiz bank.
- Read the mind map for each scenario (section 5). Print it, cover the Fix column, and fill it in from memory.
- Train on the traps (section 6). Each trap page has a simulator that shows each option playing out, then exam-style practice.
- Sit Mock #7, plain style under the 120-minute timer. It reads like the real exam.
- Review every miss with “Think it through”. Note the trap name on the option you picked. If the same trap keeps catching you, go back to its trap page.
- Keep practising with Mocks #6, #5 and #4, and the per-domain practice sets.
3 Scenarios × domains
Each scenario tests only some of the five domains. Green cells are tested, according to the official exam guide, and each links to the mind map that covers it. Grey cells are not applicable.
| Scenario | D1 Agentic 27% | D2 Tools & MCP 18% | D3 Claude Code 20% | D4 Prompts & output 20% | D5 Context 15% |
|---|---|---|---|---|---|
| 1 Customer Support Resolution Agent | ✓Support maps 1–3 | ✓MCP maps 3–4 | N/A | N/A | ✓Support maps 4–6 |
| 2 Code Generation with Claude Code | N/A | N/A | ✓Claude Code maps 1–3 | N/A | ✓Claude Code map 5 |
| 3 Multi-Agent Research System | ✓Multi-agent maps 1–3 | ✓Multi-agent map 4MCP map 4 | N/A | N/A | ✓Multi-agent maps 5–6 |
| 4 Developer Productivity with Claude | ✓Claude Code map 2 | ✓Claude Code map 6MCP maps 1–3 | ✓Claude Code maps 1, 2, 5 | N/A | N/A |
| 5 Claude Code for Continuous Integration | N/A | N/A | ✓Claude Code map 4 | ✓Extraction maps 1, 4, 5 | N/A |
| 6 Structured Data Extraction | N/A | N/A | N/A | ✓Extraction maps 1–5 | ✓Extraction map 6 |
You get 4 of the 6 scenarios, so every domain has at least one of its scenarios on your paper. Study all five.
4 The five domains (official order)
| Domain | Weight | What it covers | Lessons | Practice |
|---|---|---|---|---|
| D1 Agentic Architecture & Orchestration | 27% | The agent loop and stop_reason, subagents, hooks, enforcement vs prompting, handoffs | Lessons & quizzes | D1 practice |
| D2 Tool Design & MCP Integration | 18% | Tool descriptions, structured errors, tool_choice, MCP servers and resources, built-in tools | Lessons & quizzes · MCP skeletons | D2 practice |
| D3 Claude Code Configuration & Workflows | 20% | CLAUDE.md levels, rules with paths, commands and skills, plan mode, the CLI in CI | Lessons & quizzes · Hands-on lab | D3 practice |
| D4 Prompt Engineering & Structured Output | 20% | Explicit criteria, few-shot, JSON schemas via tool use, validation retries, batches | Lessons & quizzes | D4 practice |
| D5 Context Management & Reliability | 15% | Case-facts blocks, lost in the middle, escalation, error propagation, review sampling | Lessons & quizzes | D5 practice |
5 Mind maps
One printable page per scenario. Each map is a table of “what you see, where the fault is, the fix”, with a yellow runner-up row, the exam-guide line, and one example question.
| Page | Scenarios | The maps |
|---|---|---|
| Scenarios × domains | All | The table in section 3, on its own page |
| Support agent | 1 | When the loop stops · prompt or hook · cleaning tool results · when to escalate · several matches · keeping exact facts |
| Claude Code | 2, 4, 5 | Where an instruction lives · plan or just do it · how to iterate · Claude Code in CI · long or stale sessions · built-in tools |
| Multi-agent research | 3 | Coverage gaps · what a subagent knows · fixed or adaptive · tools per agent · failed subagents · sources and conflicts |
| MCP | 1, 3, 4 | Where the config goes · tool or resource · wrong tool picked · what a failed tool returns |
| Structured extraction | 5, 6 | JSON that always parses · schemas that don't invent · retries · consistency · batch or now · human review |
6 Trap gym: all 30 traps
One trap for each task statement in the exam guide. Each page tells a short story, lets you change the real setting in a simulator and watch the effect, and ends with exam-style practice. Open the full trap list →
| Trap | Guide | Trap | Guide |
|---|---|---|---|
| D1 Agentic Architecture | |||
| Stop reason | 1.1 | Hook to clean up data | 1.5 |
| Coordinator split | 1.2 | Fixed chain or Claude decides | 1.6 |
| Subagent context | 1.3 | Resume, fork or start fresh | 1.7 |
| Prompt or hook | 1.4, 1.5 | ||
| D2 Tool Design & MCP | |||
| Tool picker | 2.1 | tool_choice | 2.3, 4.3 |
| Tool failure | 2.2, 5.3 | MCP: where and what | 2.4 |
| Too many tools | 2.3 | Built-in tools | 2.5 |
| D3 Claude Code | |||
| Where an instruction lives | 3.1–3.3 | Examples, tests first or interview | 3.5 |
| Plan or just do it | 3.4 | Claude Code in CI | 3.6 |
| D4 Prompt Engineering & Structured Output | |||
| Explicit criteria | 4.1 | Retry with the error | 4.4 |
| Few-shot examples | 4.2 | Batch or now | 4.5 |
| Schema and nullable fields | 4.3, 4.4 | Self-review | 4.6, 3.6 |
| D5 Context Management & Reliability | |||
| Context meter | 5.1 | Empty result or failure | 5.3, 2.2 |
| Who escalates | 5.2 | Large codebase | 5.4 |
| Several customer matches | 5.2 | Confidence and sampling | 5.5 |
| Sources | 5.6 | ||
Some pages cover two traps: “Tool failure” also covers “Empty result or failure”, and “Extraction honesty” covers both schema traps.
7 Mock exams
Four full papers in plain style: 240 questions, each with “Explain simply” and “Think it through”. Take them under the 120-minute timer.
| Mock | Use it for |
|---|---|
| #7 | Start here. Reads like the real exam: every option works, and one fits best. |
| #6 · #5 · #4 | Three more full papers in the same style, on different situations. |
| Originals: #7 · #6 · #5 · #4 | Earlier versions. #7 has a replay simulator for every question. #6 is a stretch: it's harder to read than the real exam. |
| #1 · #2 · #3 | Older style. The right answer is often the longest option, so scores here overstate readiness. |
8 Reference pages
| Page | When to use it |
|---|---|
| Exam vs 2026 | Eight places where the exam's answer differs from today's API and Claude Code. Rule: answer from the guide. |
| Wire-format reference | What API requests and responses look like, with every field marked must know, recognise or skip. |
| Full study guide | All task statements in one long page. |
| MCP skeletons | Minimal MCP server and client code, to see the shapes. |
| Claude Code lab | Try CLAUDE.md, rules, commands, skills and plan mode yourself. |