Anthropic CCAR-F 試験概要:

Anthropic CCAR-F 試験シラバストピック:

Anthropic Claude Certified Architect - Foundations 認定 CCAR-F 試験問題：

問題 #1

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JSON schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.
After your daily batch of 10,000 documents completes, 300 documents (3%) fail with context_length_exceeded errors. The results file identifies each failure by custom_id.
What is the most cost-effective approach to process these failures?

A. Resubmit the entire 10,000-document batch using a model tier with a larger context window.
B. Increase the max_tokens parameter for the 300 failed documents and resubmit them in a new batch.
C. Resubmit only the 300 failed documents after chunking them into smaller pieces, and then combine the partial extractions.
D. Reprocess the entire batch with prompt caching enabled to reduce the cost of retrying requests with identical system prompts.

問題 #2

A customer returns 4 hours after the initial session about the same billing dispute. The previous
32-turn session contains lookup_order results showing "Status: PENDING, Expected resolution:
24-48 hours." In testing, you observe that when resuming sessions with stale tool results, the agent often references the outdated data in responses (e.g., "I see your refund is still being processed") even after subsequent fresh tool calls return different information. What approach most reliably handles returning customers?

A. Resume with full history and add a system prompt instruction telling the agent to always prefer the most recent tool results when multiple calls to the same tool exist in context.
B. Start a new session, inject a structured summary of the previous interaction (issue type, actions taken, resolution status), then make fresh tool calls before engaging.
C. Resume with full history but filter out previous tool_result messages before resuming, keeping only the human/assistant turns so the agent must re-fetch needed data.
D. Resume with full history and configure the agent to automatically re-call all previously-used tools at session start to ensure data freshness.

問題 #3

After investigating a billing dispute over 25+ turns, you've identified that duplicate charges occurred due to a payment gateway timeout triggering retry logic. The required refund ($847) exceeds your $500 authorization limit You need to call escalate_to_human, and the human agent won't have access to your conversation transcript. What context should you pass to enable effective resolution?

A. A structured summary: customer ID, root cause, refund amount, and recommended action.
B. Your diagnosis and the refund amount only.
C. The customer's original complaint verbatim plus the tool result excerpts showing duplicate transactions.
D. The complete conversation transcript with all tool results.

問題 #4

Which statement BEST describes Retrieval-Augmented Generation?

A. It permanently retrains Claude.
B. It supplies relevant external knowledge during inference.
C. It changes token pricing.
D. It compresses model weights.

問題 #5

A developer includes multiple unrelated tasks inside one extremely long prompt. What is the MOST likely outcome?

A. Increased prompt clarity.
B. Reduced instruction clarity.
C. Faster inference.
D. Improved reasoning.

解説：