最も有効な CCAR-F 試験参考書

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.
Your system extracts event metadata (date, location, organizer, attendee_count) from news articles using a JSON schema with all nullable fields. During evaluation, you observe the model frequently generates plausible but incorrect values for fields not mentioned in the article--for example, outputting "500" for attendee_count when the source contains no attendance information.
What's the most effective way to reduce these false extractions?

• A. Add prompt instructions to return null for any field where information is not directly stated in the source.
• B. Add a post-processing step using a second LLM call to verify each extracted value exists in the source document.
• C. Make all schema fields required (non-nullable) with strict validation rules to ensure the model only outputs verifiable data.
• D. Upgrade to a more capable model tier with improved instruction-following to reduce hallucination tendencies.

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JSON schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.
Your extraction system processes two document types: standard monthly reports, which are archived after processing, and urgent exception reports, which must trigger business alerts within
30 minutes of receipt. Both use the same JSON schema. You want to minimize API costs while meeting the latency requirements.
How should you architect the processing pipeline?

• A. Queue all documents and submit hourly batches, flagging urgent documents for expedited handling when batch results return.
• B. Submit all documents to the real-time Messages API to ensure consistent processing latency across document types.
• C. Route standard reports to the Message Batches API for 50% cost savings, and route urgent exception reports to the real-time Messages API.
• D. Submit all documents to the Message Batches API with custom_id values for tracking. When results arrive, immediately process urgent documents and trigger delayed alerts for exceptions.

A company is building its first production Claude application. Which principle should guide the initial deployment?

• A. Maximize prompt complexity immediately.
• B. Start with a simple design and iteratively evaluate improvements.
• C. Optimize only for response speed.
• D. Disable monitoring to reduce costs.

Your automated review generates many findings per pull request, but developer feedback shows that roughly half are dismissed as "not worth addressing." Analysis reveals that dismissed findings are often technically accurate but involve minor style preferences or patterns that are acceptable in your codebase. Before adding infrastructure complexity, what prompt-design change could most effectively reduce dismissals while maintaining the detection of genuine issues?

• A. Implement a secondary classification model that filters Claude's findings according to predicted developer acceptance.
• B. Ask Claude to rate every finding's confidence from 1 to 10 and include only findings rated 8 or higher.
• C. Add explicit criteria defining which issues to report, such as bugs and security defects, and which issues to skip, such as minor style preferences and accepted local patterns.
• D. Append instructions telling Claude to "only report findings you are highly confident are genuine problems."

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, and Glob--and integrates with Model Context Protocol (MCP) servers.
Engineers frequently ask the agent to cross-reference code changes with Jira tickets during reviews--checking ticket descriptions, acceptance criteria, and recent comments. This currently requires manually copying and pasting content into conversations. The team wants the agent to access this standard Jira ticket data directly.
What is the most effective approach?

• A. Integrate an existing Jira MCP server that exposes tickets, comments, and metadata through discoverable tool interfaces.
• B. Use the Bash tool with curl to call Jira's REST API, including authentication headers and parsing JSON responses inline.
• C. Build a custom MCP server wrapping Jira's API with tools designed specifically for this team's code-review workflow.
• D. Export Jira tickets to Markdown files in the repository that the agent accesses using the Read tool.