CCAR-F · Practice
CCAR-F practice questions
125 original Claude Certified Architect – Foundations questions. Pick a mode (mixed, new only, weak areas, due for review, bookmarked) and domains; every answer is explained and linked to the official docs.
- D1 Agentic Architecture & Orchestration: 20 questions
- D2 Tool Design & MCP Integration: 20 questions
- D3 Claude Code Configuration & Workflows: 30 questions
- D4 Prompt Engineering & Structured Output: 31 questions
- D5 Context Management & Reliability: 24 questions
Two sample questions
D1 · scenario S1
A support agent built with the Agent SDK uses MCP tools get_customer, lookup_order, process_refund and escalate_to_human, targeting 80% first-contact resolution. The agent occasionally issues refunds before verifying identity, despite a clear rule in the prompt. What is the most reliable fix?
- Restate the verification rule in capitals at the top and bottom of the system prompt
- Move the agent to a larger model that follows multi-step instructions more reliably
- Add ten few-shot conversations that always show verification happening before any refund
- Have process_refund reject calls until verification has succeeded in this session
D2 · scenario S1
A support agent built with the Agent SDK uses MCP tools get_customer, lookup_order, process_refund and escalate_to_human, targeting 80% first-contact resolution. process_refund takes an order_id and an amount. Twice this month, a customer disputed one item and the agent refunded the whole order. What is the best change?
- Lower the temperature so the agent picks refund amounts more consistently
- Add a system prompt rule telling the agent to refund only the disputed items
- Require the agent to call lookup_order right before every process_refund call
- Make the tool take line-item IDs and compute the amount itself, rejecting others