Anthropic CCAR-F : Claude Certified Architect - Foundations

The synthesis agent completes its initial pass but flags that three key research questions remain unanswered because the web search and document analysis agents didn't find relevant information on those specific subtopics. The coordinator currently proceeds directly to report generation, producing reports with incomplete coverage. What change would most effectively improve research completeness?

• A. Give the synthesis agent direct access to web search tools so it can autonomously fill knowledge gaps without returning control to the coordinator.
• B. Have the report generation agent note which research questions couldn't be answered, so users understand the limitations of the final output.
• C. Have the coordinator evaluate synthesis output for gaps, then re-delegate to web search and document analysis with targeted queries before invoking synthesis again.
• D. Increase the initial breadth of queries sent to web search and document analysis to reduce the probability of missing relevant information.

Which prompt revision is MOST likely to improve output quality?

• A. "Help me."
• B. "Summarize this."
• C. Include objective, context, constraints, and expected format.
• D. Use only uppercase letters.

Your agent has called lookup_order multiple times while investigating a customer's return requests. Each response includes 40+ fields (items, shipping details, payment info, status history). Tool outputs now represent the majority of the conversation's context. The customer mentions two more orders they want to discuss. What's the most effective approach before making additional lookups?

• A. Move all tool responses to a vector database with semantic indexing, retrieving relevant portions as the conversation continues
• B. Have the model generate a natural language summary of each order's key details, replacing structured responses with prose descriptions
• C. Extract only the return-relevant fields (items, purchase date, return window, status) from each existing order response, removing verbose details
• D. Proceed with additional lookups without modifying the existing tool output context

A legal department requires Claude to answer only when sufficient evidence exists in retrieved documents. What should Claude do if evidence is insufficient?

• A. Invent a likely answer.
• B. Clearly indicate insufficient information.
• C. Increase creativity.
• D. Search social media automatically.

Compliance requires that refunds exceeding $500 must automatically escalate to a human agent
- this rule cannot be left to model discretion. Despite clear system prompt instructions, production logs show the agent occasionally processes high-value refunds directly (3% failure rate). How should you achieve guaranteed compliance?

• A. Add few-shot examples to the prompt showing correct escalation behavior at various refund amounts ($400, $500, $600).
• B. Modify the refund tool to return an error with message "Amount exceeds policy limit - please escalate" when threshold is exceeded.
• C. Strengthen the system prompt with emphatic language: "CRITICAL POLICY: Refunds over $500 MUST trigger human escalation. NEVER process these directly."
• D. Implement a hook to intercept tool calls; when the refund process amount exceeds $500, block it and invoke human escalation.