Claude Architect Foundations Mock Test 2 (30 Questions)
← All Claude certification mock tests
Mock Test 2 for the Claude Certified Architect – Foundations (CCAR-F) exam: 30 scenario-based questions, a 60-minute timer and a 72% pass mark. Scenarios in this test: Multi-Agent Research System, Developer Productivity with Claude, Structured Data Extraction. Submit to see your score, a per-domain breakdown and an explanation for every option.
What this mock test covers
- Agentic Architecture & Orchestration — 8 questions
- Tool Design & MCP Integration — 6 questions
- Claude Code Configuration & Workflows — 4 questions
- Prompt Engineering & Structured Output — 7 questions
- Context Management & Reliability — 5 questions
Review these lessons before or after the test:
- Claude Agentic Loop: stop_reason, Tool Results and Anti-Patterns
- Multi-Agent Orchestration with Claude: Coordinators and Subagents
- Claude Agent SDK Hooks, Prerequisite Gates and Human Handoffs
- Task Decomposition and Session Management in Claude Code
- Claude Tool Design: Descriptions, Tool Distribution and tool_choice
- MCP Tool Error Handling: isError, Error Categories and Retries
- MCP Integration in Claude Code: Scopes, Resources and Built-in Tools
- CLAUDE.md Configuration Guide: Hierarchy, @import and Path-Specific Rules
- Claude Code Slash Commands and Skills (SKILL.md Frontmatter)
- Claude Code Plan Mode vs Direct Execution and Iterative Refinement
- Claude Code in CI/CD: -p Flag, JSON Output and Automated PR Review
- Prompt Engineering for Claude: Explicit Criteria and Few-Shot Examples
- Claude Structured Output with tool_use and JSON Schema
- Claude Message Batches API and Multi-Pass Review Design
- Claude Context Management: Case Facts, Lost-in-the-Middle and /compact
- Escalation Rules and Error Propagation in Claude Agents
- Human Review, Confidence Calibration and Source Provenance
Sample questions with answers
These practice questions are not part of the timed test above.
Sample question 1
After executing the three tool calls Claude requested in one turn, how should you return the results?
- A. Three separate user messages, one per result
- B. Put the results in the system prompt
- C. One assistant message with the results
- D. One user message containing three `tool_result` blocks, each with its `tool_use_id`
Answer: D. All results for a turn go back in one user message, matched by ID. A: splitting them breaks the turn structure and discourages parallel calls. B and C: results are user-role content, not system or assistant content.
Sample question 2
"Review this PR": each of 9 files should get the same checklist, followed by a cross-file data-flow check. Which decomposition fits?
- A. Three random full-PR passes with voting
- B. Dynamic adaptive decomposition
- C. A single pass with a larger context
- D. Prompt chaining: per-file passes, then an integration pass
Answer: D. Predictable, multi-aspect work suits a fixed chain. B suits open-ended investigation. C: attention gets diluted. A: voting suppresses real but intermittent findings.
Sample question 3
Which error should **not** be retried?
- A. Network timeout
- B. 503 Service Unavailable
- C. Rate limited
- D. "Refund exceeds the 30-day policy window"
Answer: D. A business-rule violation: retrying won't change the outcome, so explain it or escalate. B, A and C are transient.
Sample question 4
A skill should only write files and never run Bash. Which frontmatter enforces this?
- A. `context: fork`
- B. `paths`
- C. `argument-hint`
- D. `allowed-tools: Write, Edit` (or similar, excluding Bash)
Answer: D. It restricts the tools available during the skill. A isolates context. C prompts for arguments. B belongs to rules.
Sample question 5
Severity labels are inconsistent across runs. What helps most?
- A. Define each severity level with concrete code examples
- B. Increase the temperature
- C. Use only two levels
- D. Ask Claude to be consistent
Answer: A. Concrete anchors give consistent classification. D is vague. C loses information without fixing the ambiguity. B makes it worse.
Sample question 6
Aggregated subagent results put the key findings in the middle of a 60-page input, and the synthesis misses them. What helps?
- A. Remove the headers
- B. Increase the temperature
- C. Shuffle the order
- D. Put a key-findings summary at the beginning and organise the details under clear section headers
Answer: D. It mitigates the "lost in the middle" effect. C, A and B don't address position effects.
Frequently asked questions
How many questions are in this mock test?
30 questions in 60 minutes, the same pace as the real 60-item, 120-minute exam.
What score do I need?
72% passes this mock. Aim for 85% or more on at least three mocks before booking the real exam.
Can I retake the test?
Yes, as often as you like. Answer options are reshuffled each time. Try the other mocks too: Mock Test 1 · Mock Test 3 · Mock Test 4 · Mock Test 5.
Are these real exam questions?
No. They are original practice questions written against the official CCAR-F exam objectives.
Independent study material by SQA Tools. Not affiliated with, endorsed by or sponsored by Anthropic. Claude is a trademark of Anthropic. Mock questions are original practice items, not real exam content. Exam facts checked against Anthropic's official exam guides and certification FAQ on 11 November 2026.