Anthropic CCAR-F 問題集 : Claude Certified Architect - Foundations

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.
Your schema includes a skills: string[] field. Production monitoring reveals three consistency issues:
(1) compound phrases like "Python and SQL" are sometimes kept as one
entry, sometimes split;
(2) implied but unstated skills occasionally appear in extractions;
(3) similar documents produce wildly different array lengths (5-10 vs
40+ entries).
Your prompt currently says "Extract all skills mentioned."
What's the most effective improvement?

• A. Add constraints: "Extract 10-20 skills maximum, one skill per entry, only explicitly named skills."
• B. Add post-extraction normalization that maps skills to a canonical taxonomy and deduplicates similar entries.
• C. Enrich the schema to {skill: string, confidence: float, source_quote: string}[] to capture extraction metadata.
• D. Add few-shot examples demonstrating compound phrase handling, explicit mention criteria, and appropriate entry granularity.

An application frequently repeats the same background instructions in every API request. What is a potential downside?

• A. Lower reliability.
• B. Higher token usage and cost.
• C. Increased hallucinations only.
• D. Reduced model capability.

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.
Your extraction pipeline processes contracts that frequently include amendments. When a contract contains both original terms and later amendments (e.g., original clause specifies "30- day payment terms" while Amendment 1 changes this to "45 days"), the model inconsistently extracts one value or the other with no indication of which applies.
What's the most effective approach to improve extraction accuracy for documents with amendments?

• A. Redesign the schema so amended fields capture multiple values, each with source location and effective date.
• B. Add prompt instructions to always extract the most recent amendment value and ignore superseded original terms.
• C. Implement post-extraction validation using pattern matching to detect amendments and flag those extractions for manual review.
• D. Preprocess documents with a classifier that identifies and removes superseded sections before the main extraction step.

A financial services company plans to integrate Claude into an internal document analysis platform. The architects want to minimize exposure of confidential client information while maintaining high-quality responses. Which approach BEST aligns with Anthropic's recommended architecture?

• A. Send every document without preprocessing to maximize context.
• B. Store every prompt permanently for auditing.
• C. Replace Claude with a smaller local model regardless of task complexity.
• D. Remove unnecessary sensitive information before sending prompts whenever possible.

Production logs show that when the agent handles complex billing disputes requiring 6+ tool calls, it sometimes exhausts its max_turns limit after gathering data but before completing resolution or escalating. The team's goal is to guarantee that every customer interaction ends with either a completed resolution or a human handoff, regardless of how the agent loop terminates. Which approach achieves this guarantee?

• A. Split the workflow into two sequential agent invocations - a first agent gathers information via get_customer and lookup_order, then a second agent receives that data and handles process_refund or escalate_to_human, each with separate turn budgets.
• B. Add orchestration-layer code that checks the agent's outcome after each loop termination - if the loop ended without a completed resolution or escalation, programmatically call escalate_to_human with the accumulated conversation context and tool results.
• C. Add system prompt instructions telling the agent to call escalate_to_human with a summary of its findings whenever it determines it cannot complete resolution within its remaining actions.
• D. Implement a pre-tool-use hook that counts tool invocations and terminates the loop with an automatic escalation once the agent reaches 80% of its max_turns limit.