Try Anthropic : CCAR-F practice torrent pass for sure

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. Expand the description field with more detailed explanations of why each issue matters and how it should be fixed.
• B. Remove the issue_category field and track dismissal rates only at the individual-finding level.
• C. Add a detected_pattern field recording the specific code construct that triggered the finding, such as single-letter loop variable.
• D. Add a model_confidence field from 0.0 to 1.0 and filter findings below a threshold calibrated against historical dismissal rates.

Explanation: Only visible for SureTorrent members. You can sign-up / login (it's free).

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 test generation produces unit tests for new code, but reviews show that 55% are low-value:
trivial assertions that only verify functions do not throw exceptions, tests duplicating existing coverage, or tests ignoring your team's fixture conventions.
How do you reduce the rate of low-value tests being generated in the first place?

• A. Implement two-phase generation in which a second Claude call scores each test against quality criteria, filtering out low-scoring tests before presenting results to developers.
• B. Document testing standards in CLAUDE.md, including valuable-test criteria, available fixtures and their intended use cases, and examples distinguishing meaningful behavioral tests from trivial assertions.
• C. Add post-generation coverage analysis that automatically filters out any generated test that does not increase line coverage beyond existing tests.
• D. Restrict test generation to directories where historical quality metrics show higher acceptance rates, disabling it for areas where generated tests consistently require substantial editing.

Explanation: Only visible for SureTorrent members. You can sign-up / login (it's free).

A company wants Claude to summarize thousands of support tickets efficiently. Which design scales BEST?

• A. Send all tickets in one request.
• B. Process tickets individually and combine summaries.
• C. Increase temperature.
• D. Remove system prompts.

Explanation: Only visible for SureTorrent members. You can sign-up / login (it's free).

You are building developer productivity tools using the Claude Agent SDK. The agent helps engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate code, and automate repetitive tasks. It uses the built-in tools (Read, Write, Bash, Grep, Glob) and integrates with Model Context Protocol (MCP) servers.
During testing, you observe that in extended exploration sessions (30+ minutes), the agent starts giving inconsistent answers about code structure it discussed earlier. Engineers report having to repeat context about modules they've already explored. What's the most effective approach to address this?

• A. Create summaries of all source files before exploration begins, loading only these compressed representations into context.
• B. Have the agent maintain a scratchpad file that records key findings, referencing it for subsequent questions.
• C. Switch to a higher-capacity model tier to provide more context window space for accumulated exploration data.
• D. Implement automatic context clearing every 15 minutes to ensure the agent starts with fresh, uncontaminated context.

Explanation: Only visible for SureTorrent members. You can sign-up / login (it's free).

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

Explanation: Only visible for SureTorrent members. You can sign-up / login (it's free).