Anthropic CCA-F 問題集 : Claude Certified Architect Foundations (CCA-F)

A customer writes: "I've been going back and forth on this return for days. I just want to speak to someone who can actually help me." The agent has confirmed via lookup_order that the return is straightforward - within policy and eligible for immediate processing. What should the agent do?

• A. Process the refund via process_refund to resolve the underlying issue, then inform them it's complete
• B. Ask what specifically hasn't worked in previous attempts before deciding whether to escalate or resolve automatically
• C. Acknowledge frustration, inform them this is resolvable now, and offer to complete it or escalate
• D. Call escalate_to_human immediately to honor the customer's request

An enterprise wants Claude responses to remain professional across every interaction. Where should tone instructions primarily reside?

• A. System prompt
• B. API key description
• C. Retrieved documents
• D. User prompt only

Your process_refund tool returns two types of errors: technical errors ("503 Service Unavailable",
"Connection timeout") that are transient (5% of calls), and business errors ("Order exceeds
30 day return window", "Item already refunded") that are permanent (12% of calls). Monitoring shows the agent wastes 3-4 turns retrying business errors that can never succeed. Currently, both error types return only a plain text message to Claude. What's the most effective way to reduce wasted retries while improving customer-facing response quality?

• A. Add a check_refund_eligibility tool that must be called before process_refund to prevent business rule violations.
• B. Implement automatic retry logic at the tool level for technical errors only, passing business errors to Claude without retries.
• C. Add few-shot examples showing how to distinguish retriable from non-retriable errors by parsing error message text.
• D. Return structured error responses with retriable: false for business errors and a customer-friendly explanation for Claude to use.

You've configured the system so that all four subagents have access to the complete set of
18 tools. During testing, agents frequently call tools outside their specialization - the synthesis agent attempts web searches, and the report generator tries to analyze documents. What is the primary cause of this poor tool selection behavior?

• A. The agents' role descriptions in their system prompts conflict with having access to tools outside that role.
• B. Choosing from 18 tools instead of 4-5 relevant ones increases decision complexity beyond reliable selection thresholds.
• C. The tool definitions consume too much context window space, leaving insufficient room for task content.
• D. The coordinator cannot track which capabilities each subagent has, leading to misrouted tasks.

Your product search tool queries an external catalog API and returns matching items. In production, you observe the agent frequently retries searches immediately after receiving zero results, treating "no matches found" as a failure requiring retry. The external API returns HTTP 200 with an empty results array - a valid response. How should you restructure the tool's result to help the agent correctly interpret empty result sets?

• A. Return a structured result with a success boolean and results array, reserving isError: true for actual execution failures only.
• B. Return a result object with isError: true and a message explaining no products matched.
• C. Return a natural language string describing the outcome, allowing the agent to interpret the result contextually based on the message content.
• D. Add a suggestions field containing alternative search strategies when results are empty, helping guide the agent toward more productive follow-up queries.