Free Anthropic CCAR-F Exam Questions

Question 1

You built an LLM-powered code-review tool that analyzes pull requests and returns structured findings. Each finding is a JSON object containing file_path, line_number, issue_category—such as security or style—and description. Developers can dismiss findings they consider unhelpful, and currently 35% of findings are dismissed. You want to analyze these dismissals to understand what the system is getting wrong and improve the prompts accordingly. What change to the output structure would best support this analysis?

A : Add a model_confidence field from 0.0 to 1.0 and filter findings below a threshold calibrated against historical dismissal rates.

B : Add a detected_pattern field recording the specific code construct that triggered the finding, such as single-letter loop variable.

C : Expand the description field with more detailed explanations of why each issue matters and how it should be fixed.

D : Remove the issue_category field and track dismissal rates only at the individual-finding level.

Answer: B

Question 2

The web-search agent has gathered several relevant sources for a research topic. The document-analysis agent now needs to examine those sources. How does information typically flow between these two specialized subagents?

A : The coordinator receives the web-search agent’s output and includes the relevant sources and findings in the prompt used to invoke the document-analysis agent.

B : The web-search agent directly invokes the document-analysis agent and passes the discovered sources as parameters.

C : The agents communicate through an event-driven message queue, with the document-analysis agent subscribing to web-search completion events.

D : Both agents automatically access a shared memory store in which the web-search agent writes its findings.

Answer: A

Question 3

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?

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 4

You are building a structured data extraction system using Claude. The system extracts information fromunstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, andmaintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.The system needs to extract candidate information (name, contact details, skills, work experience, education)from uploaded resumes. The extracted data must strictly conform to a predefined JSON schema, as missingrequired fields or incorrect data types will cause downstream validation failures.What is the most reliable approach to ensure Claude’s output consistently matches the schema?

A : Parse Claude’s text response with regex patterns to extract JSON objects, using retry logic for malformed responses.

B : Include detailed JSON formatting instructions and a template example in the system prompt, asking Claude to output only valid JSON.

C : Make two separate API calls—first extracting information as text, then asking Claude to format that text as JSON.

D : Define a tool with an input schema matching your required JSON structure and extract the data from Claude’s tool_use response.

Answer: D

Question 5

You are building a structured data extraction system using Claude. The system extracts information fromunstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, andmaintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.Monitoring shows 12% of extractions fail Pydantic validation with specific errors like “expected float forquantity, got ‘2 to 3’”. Retrying these requests without modification produces identical failures.What’s the most effective approach to recover from these validation failures?

A : Send a follow-up request including the validation error, asking the model to correct its output.

B : Set temperature to 0 to eliminate output variability and ensure consistent formatting.

C : Pre-process source documents to standardize problematic formats before sending them for extraction.

D : Implement a secondary pipeline using a larger model tier to reprocess documents that fail validation.

Answer: A