Question 1

You are building a customer support resolution agent using the Claude Agent SDK. The agent handles highambiguity 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.

During testing, you find that when a customer says “I need a refund for my recent purchase,” the agent calls

process_refund immediately—but populates the required order_id parameter with a plausible-looking but

fabricated value instead of first calling lookup_order to retrieve the actual order ID. The refund call fails

because the fabricated ID doesn’t exist.

Which change directly addresses the root cause of the agent fabricating the order_id value?

Options :

A : Update the process_refund tool description to explicitly state that order_id must be obtained from a prior lookup_order call and must never be assumed or invented.

B : Switch tool_choice from " auto " to " any " to force the agent to make a tool call on every turn.

C : Add server-side validation that checks whether the order_id exists in your database before executing the refund, returning an error to the agent if not found.

D : Pre-parse incoming customer messages to extract any order IDs mentioned, and inject them into the conversation context before passing to Claude.

Answer: A

Question 2

Your automated reviewer uses a single prompt covering security issues, API design, and business-logic correctness. Your evaluation suite shows strong recall for API-design findings at 82% but poor recall for business-logic edge cases in quiz scoring at 34%. When you add few-shot examples of logic bugs to the prompt, logic recall improves to 41%, but API-design recall drops to 68%. How should you address this tradeoff to improve detection across both categories?

Options :

A : Provide the full repository as context instead of only the changed files and surrounding code, giving the model deeper visibility into business-logic patterns.

B : Replace the few-shot examples with a detailed checklist of specific logic edge cases to verify, such as division by zero in score calculations and boundary conditions in grading thresholds.

C : Split the review into separate focused prompts—one for security and API design and another for business logic—each with dedicated examples, and then consolidate the findings before posting.

D : Upgrade to a more capable model tier because its stronger reasoning will handle both concern types in a single prompt and eliminate the recall trade-off.

Answer: D

Question 3

In production, you observe that simple fact-checking queries—for example, “What year was the Paris Climate Agreement signed?”—traverse all four subagents sequentially, consuming more than 40 seconds and significant tokens per query. Complex comparative research benefits from the full pipeline. Your query distribution is diverse and evolving as users discover new applications. What is the most effective approach to optimize for varying query complexity?

Options :

A : Create a fast path for factual questions that bypasses subagents entirely, routing all other queries through the complete pipeline to ensure research thoroughness.

B : Train a query-complexity classifier on labeled historical data to predict optimal subagent combinations, retraining it periodically as query patterns evolve.

C : Have the coordinator analyze each query and dynamically decide which subagents to invoke based on its assessment of the query requirements.

D : Implement pattern-based routing that categorizes queries by structure—single-fact, comparative, or analytical—and maps each category to a predefined subagent combination.

Answer: C

Question 4

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline.

The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You

need to design prompts that provide actionable feedback and minimize false positives.

Your pipeline includes a release-notes generation step that classifies and summarizes approximately 200

commits at the end of each weekly release cycle. Each commit is currently sent as a separate Messages API

request using a Sonnet-tier Claude model. The release notes are not needed until the following morning,

providing approximately 12 hours of acceptable latency.

Your team must reduce the per-token API cost while retaining the same model, prompts, and output quality.

Which approach satisfies all these constraints?

Options :

A : Issue the 200 Messages API requests concurrently because parallel execution reduces the per-token price.

B : Submit the 200 requests through the Message Batches API with unique custom_id values and retrieve the results after the batch finishes.

C : Concatenate all 200 commit messages into one Messages API request because reducing the number of requests always reduces token costs.

D : Replace the Sonnet-tier model with a Haiku-tier model to obtain a lower per-token price.

Answer: B

Question 5

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives. Your automated reviewer uses a single prompt covering security issues, API design, and business-logic correctness. Your evaluation suite shows strong recall for API-design findings at 82% but poor recall for business-logic edge cases in quiz scoring at 34%. When you add few-shot examples of logic bugs to the prompt, logic recall improves to 41%, but API-design recall drops to 68%. How should you address this trade-off to improve detection across both categories?

Options :

A : Split the review into separate focused prompts—one for security and API design and another for business logic—each with dedicated examples, and then consolidate the findings before posting.

B : Replace the few-shot examples with a detailed checklist of specific logic edge cases to verify, such as division by zero in score calculations and boundary conditions in grading thresholds.

C : Upgrade to a more capable model tier because its stronger reasoning will handle both concern types in one prompt and eliminate the recall trade-off.

D : Provide the full repository as context instead of only the changed files and surrounding code, giving the model deeper visibility into business-logic patterns.

Answer: A

Confidently Practice Online with Free CCAR-F Exam Cram

Buying Options: