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 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.
• B. Return fields organized into verified and needs_verification objects based on confidence thresholds.
• C. 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.
• D. 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.

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.
During initial testing of the automated review pipeline, you notice that reviews on large pull requests containing more than 50 changed files sometimes take over 20 minutes and cost $8?12 per run because of extensive agentic loops. Claude reads files, runs analysis tools, and iterates many times. Your team needs each invocation to abort once it reaches both a fixed iteration count and a fixed dollar amount, enforced by Claude Code itself rather than by the surrounding job runner.
Which configuration change directly enforces both per-invocation caps?

• A. Switch the --model flag to a smaller, less expensive model so each iteration uses fewer tokens and has a lower per-call cost.
• B. Set --permission-mode dontAsk to automatically deny tool-permission requests not included in the explicitly allowed set.
• C. Set timeout-minutes: 5 on the GitHub Actions job step and monitor per-run costs through the Anthropic Console usage dashboard.
• D. Add --max-turns 10 --max-budget-usd 2.00 to the claude -p invocation to cap iterations and spending.

You are using Claude Code to accelerate software development. Your team uses it for code generation, refactoring, debugging, and documentation. You need to integrate it into your development workflow with custom slash commands, CLAUDE.md configurations, and understand when to use plan mode vs direct execution.
You're tasked with adding real-time updates to the application. This could be implemented using WebSockets, Server-Sent Events, or polling, each with different complexity, browser support, and infrastructure requirements.
What's the most effective way to begin this task?

• A. Enter plan mode to explore the architecture, evaluate trade-offs, and present options for team approval before implementing.
• B. Use direct execution to implement polling first, then evaluate whether to upgrade to WebSockets later.
• C. Start direct execution with WebSockets, then refactor if infrastructure issues arise.
• D. Use direct execution with a prompt asking Claude to analyze all approaches and implement the one it determines is best.

What is the PRIMARY purpose of few-shot prompting?

• A. Increase model size.
• B. Demonstrate desired output patterns.
• C. Encrypt prompts.
• D. Reduce token costs.

Users report that final reports sometimes lack depth on specific subtopics. Investigation shows that the document-analysis agent frequently identifies evidence gaps--for example, noting that
"the retrieved sources discuss API authentication but lack details about token-refresh patterns." Under the current strict pipeline, this insight is not actionable because searching has already finished. What is the most effective architectural change?

• A. Add a research-planning agent before the initial search phase to decompose every topic into detailed subquestions.
• B. Have the synthesis agent assign confidence scores to each report section and flag insufficiently supported sections for manual review.
• C. Require the analysis agent to return specific evidence gaps to the coordinator, which launches targeted searches and invokes analysis again until the defined coverage criteria are satisfied.
• D. Have the coordinator look for general gap indicators in the analysis output and run additional searches without repeating the analysis stage.