CCA-F最も有効な質問と解答で勉強

Your content curation agent discovers articles, analyzes each for relevance, then adds selected articles to themed collections. With separate discover_articles(topic), analyze_article(id), and add_to_collection(article_id, collection_id) tools, you observe 18+ sequential tool calls per request, causing latency issues. The agent must make editorial judgments about which articles fit a collection's theme - this requires seeing all candidates with their analysis scores simultaneously to select a cohesive set. What tool composition best addresses efficiency while preserving editorial judgment?

• A. Add a preview_curation(topic, collection_id) tool that shows what would be added based on predefined rules, with an approve_curation() tool to confirm.
• B. Create a curate_collection(topic, collection_id) tool that handles discovery, analysis, and selection internally using configurable quality thresholds.
• C. Keep all tools separate but implement response caching for analyze_article calls.
• D. Create a discover_and_analyze(topic) composite tool that returns all candidates with their analysis scores, keeping add_to_collection separate for selective calls.

You are building a customer support resolution agent using the Claude Agent SDK. The agent handles high-ambiguity requests like returns, billing disputes, and account issues. It has access to your backend systems through custom Model Context Protocol (MCP) tools ( get_customer, lookup_order , process_refund , escalate_to_human ). Your target is 80%+ first-contact resolution while knowing when to escalate.
After expanding the agent's MCP tools with delivery-specific capabilities ( check_delivery_status , contact_driver , issue_credit , apply_promo_code , update_delivery_address , reschedule delivery ), the total tool count has grown from 4 to 10. Your evaluation suite shows tool selection accuracy has dropped from 88% to 71%. Log analysis reveals the majority of errors involve the agent selecting between semantically overlapping tools - calling issue_credit when process_refund was correct, and calling check_delivery_status when lookup_order already returns the needed data. Which approach structurally eliminates the semantic overlap identified in the logs as the error source?

• A. Split the tools across two sub-agents - a "financial resolution" agent with process_refund , issue_credit ,and apply_promo_code , and a "delivery operations" agent with the remaining delivery tools - with a coordinator routing between them.
• B. Add few-shot examples to the system prompt demonstrating correct selection for each ambiguous tool pair, such as showing when issue_credit applies versus when process_refund is appropriate.
• C. Enable the tool search tool with defer_loading on the six new tools, keeping the original four always loaded, so the agent dynamically discovers specialized tools only when needed.
• D. Consolidate semantically overlapping tools - merge issue_credit and process_refund into a single resolve_compensation tool with an action parameter, and fold check_delivery_status into lookup_order with an optional include_tracking flag.

You're implementing the escalation logic for when the agent should call escalate_to_human. Your team proposes four different approaches for triggering escalation. Which approach will most reliably identify cases that genuinely require human intervention?

• A. Implement sentiment analysis that monitors for frustration indicators (negative language, repeated questions, exclamation marks) and trigger escalation when the frustration score exceeds a configured threshold.
• B. Instruct the agent to escalate when the customer requests a human, when the issue requires policy exceptions, or when the agent cannot make meaningful progress.
• C. Build a rules engine that maps specific issue types, customer segments, and product categories to escalation decisions, removing the need for model judgment calls.
• D. Configure the agent to escalate after three consecutive tool calls that fail to resolve the customer's stated issue, ensuring a reasonable attempt before involving a human.

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

Your document extraction tool uses ML models to extract invoice fields (vendor, amount, date).
The models return confidence scores (0.0-1.0) for each extracted field. In production, you observe: (1) the agent proceeds with low-confidence extractions that are incorrect 23% of the time, and (2) the agent requests unnecessary human review for 31% of extractions that were actually correct. How should you restructure the tool's output?

• A. Return fields with confidence scores, plus a request_review boolean computed using your tested confidence thresholds, along with a review_reasons array explaining which fields triggered review.
• B. Return fields with their raw confidence scores and add detailed few-shot examples to your system prompt demonstrating how to interpret different confidence ranges and when to request human review.
• C. Return fields organized into verified and needs_verification objects based on confidence thresholds.
• D. Compute an aggregate extraction_quality score across all fields and return it alongside the extracted values. Include a text summary describing the overall extraction reliability.