CCAR-F問題集、Anthropic実際の試験問題

質問 1

Your automated review CI jobs take 18 seconds to initialize before Claude begins analyzing code.
Profiling reveals that the delay comes from automatically discovering hooks, MCP servers, plugins, skills, and multiple nested CLAUDE.md files throughout your monorepo. You need to reduce startup time while ensuring that reviews still enforce your team's coding standards, which are documented in the root-level CLAUDE.md file. What is the most effective approach?

A. Run in --bare mode and pass --append-system-prompt-file ./CLAUDE.md to explicitly load your project standards while skipping all automatic discovery.

B. Run in --bare mode and specify all review criteria directly in the -p prompt argument for every CI invocation, without referencing external files.

C. Replace the default prompt entirely by using --system-prompt-file ./CLAUDE.md, which bypasses default prompt assembly and loads only your project rules.

D. Keep the default initialization and add --exclude-dynamic-system-prompt-sections to reduce per- machine prompt variability and improve prompt-cache hit rates across runners.

正解: A

解説: (PassTest メンバーにのみ表示されます)

質問 2

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

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

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

正解: B

解説: (PassTest メンバーにのみ表示されます)

質問 3

The coordinator provides detailed step-by-step instructions to the web-search subagent, specifying exact search queries, source priorities, and date filters. Production monitoring reveals three issues:
(1) the subagent reports "insufficient results" instead of trying
alternative approaches when the specified searches fail,
(2) research quality drops for emerging topics that do not match
expected patterns, and
(3) the subagent rarely surfaces valuable tangential sources.
What is the most effective way to improve subagent adaptability?

A. Add fallback directives requiring alternative query formulations whenever the specified searches produce fewer than a predetermined number of results.

B. Specify research objectives and quality criteria--such as coverage breadth, source diversity, and recency--rather than prescribing procedural steps, allowing the subagent to determine its search strategy.

C. Classify each topic as either "well-defined" or "exploratory" and use a different instruction style for each category.

D. Remove procedural details entirely and delegate using simple goals such as "research this topic thoroughly," relying on the subagent's general capabilities.

正解: B

解説: (PassTest メンバーにのみ表示されます)

質問 4

A prompt asks Claude to produce Markdown tables. Which addition MOST increases consistency?

A. Omit examples.

B. Increase randomness.

C. Remove formatting instructions.

D. Specify exact column names.

正解: D

解説: (PassTest メンバーにのみ表示されます)

質問 5

You are building a multi-agent research system using the Claude Agent SDK. A coordinator agent delegates to specialized subagents: one searches the web, one analyzes documents, one synthesizes findings, and one generates reports. The system researches topics and produces comprehensive, cited reports.
A user is expanding the research system beyond its single web search agent by adding specialized data sources. They add a financial API agent that returns structured JSON with revenue, margins, and growth rates; a news monitoring agent that returns prose summaries of recent developments; and a patent analysis agent that returns structured lists of technology areas. The synthesis agent combines these into executive briefings. Currently, it converts everything to bullet points, causing financial comparisons to lose tabular clarity and news summaries to lose narrative flow. What change would most improve briefing quality?

A. Standardize all subagent outputs to prose summaries with inline citations

B. Add a format conversion layer between subagents and synthesis that transforms all outputs to a common intermediate representation

C. Update the synthesis agent to render each content type appropriately - financial data as tables, news as prose

D. Standardize all subagent outputs to JSON with fields for claim, evidence, source, and confidence

正解: C

解説: (PassTest メンバーにのみ表示されます)

質問 6

You are building a multi-agent research system using the Claude Agent SDK. A coordinator agent delegates to specialized subagents: one searches the web, one analyzes documents, one synthesizes findings, and one generates reports. The system researches topics and produces comprehensive, cited reports.
When researching "renewable energy adoption," the web search agent returns recent statistics (2024: 35% adoption) while the document analysis agent extracts data from internal reports (2021: 18% adoption). The synthesis agent incorrectly flags these as contradictory sources rather than recognizing the data shows growth over time. What change would best enable the synthesis agent to correctly interpret such temporal differences?

A. Configure the web search agent to only return results from the past 6 months.

B. Require subagents to include publication or data collection dates in their structured outputs.

C. Instruct the synthesis agent to always treat the most recent data as authoritative and place older findings in a separate historical appendix.

D. Add a conflict resolution agent that automatically discards older data when newer data exists for the same metric.

正解: B

解説: (PassTest メンバーにのみ表示されます)

質問 7

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 need to add a date validation check ensuring event dates are in the future. This requires adding a conditional statement to one existing function in a single file. What is the most appropriate approach?

A. Start with extended thinking mode enabled to ensure thorough reasoning about the validation logic.

B. Enter plan mode first to create a detailed implementation strategy before making the change.

C. Enter plan mode to analyze how the validation might impact other parts of the reservation flow.

D. Use direct execution to make the change.

正解: D

解説: (PassTest メンバーにのみ表示されます)

質問 8

Your agent has called lookup_order multiple times while investigating a customer's return requests. Each response includes 40+ fields (items, shipping details, payment info, status history). Tool outputs now represent the majority of the conversation's context. The customer mentions two more orders they want to discuss. What's the most effective approach before making additional lookups?

A. Move all tool responses to a vector database with semantic indexing, retrieving relevant portions as the conversation continues

B. Extract only the return-relevant fields (items, purchase date, return window, status) from each existing order response, removing verbose details

C. Have the model generate a natural language summary of each order's key details, replacing structured responses with prose descriptions

D. Proceed with additional lookups without modifying the existing tool output context

正解: B

解説: (PassTest メンバーにのみ表示されます)

質問 9

After integrating a local MCP server providing code analysis tools (analyze_dependencies, find_dead_code, calculate _complexity), you verify the server is healthy and tools appear in the tools/list response. However, you observe that the agent consistently uses Grep to search for import statements instead of calling analyze_dependencies -even when users explicitly ask about "code dependencies." Examining tool definitions reveals:
MCP: analyze_ dependencies - "Analyzes dependency graph"
Built-in: Grep - "Search file contents for a pattern using regular
expressions. Returns matching lines with line numbers and surrounding
context."
What's the most effective approach to improve the agent's selection of MCP tools?

A. Remove Grep from available tools when the MCP server is connected to eliminate functional overlap.

B. Expand MCP tool descriptions to detail capabilities and outputs - e.g., "Builds dependency graph showing direct imports, transitive dependencies, and cycles."

C. Split analyze_dependencies into granular tools ( list_imports, resolve_transitive_deps, detect_circular_deps) so each has a focused purpose less likely to overlap with Grep.

D. Add routing instructions to the system prompt specifying that dependency-related questions should use MCP tools rather than Grep.

正解: B

解説: (PassTest メンバーにのみ表示されます)

質問 10

The coordinator agent has AgentDefinitions configured for all four specialized subagents, each with appropriate descriptions, prompts, and tool restrictions. During testing, you notice the coordinator correctly reasons about when to delegate - it generates messages like "I'll ask the web search agent to find sources on this topic" - but no subagent execution ever occurs. The coordinator then proceeds as if the delegation happened and continues with incomplete information. Logs show no errors. What is the most likely cause?

A. Subagent context isolation means task descriptions from the coordinator don't automatically reach subagents; you need to configure explicit context forwarding in ClaudeAgentOptions.

B. The coordinator's allowedTools configuration doesn't include "Task", so while it can reason about delegation, it cannot invoke the tool required to spawn subagents.

C. The AgentDefinitions are configured correctly, but the coordinator's system prompt doesn't explicitly list the available subagent types, preventing the model from knowing they can be invoked.

D. The coordinator's max_tokens setting is too low, causing the Task tool invocation to be truncated before the subagent type parameter can be specified.

正解: B

質問 11

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.
After your daily batch of 10,000 documents completes, 300 documents (3%) fail with context_length_exceeded errors. The results file identifies each failure by custom_id.
What is the most cost-effective approach to process these failures?

A. Resubmit only the 300 failed documents after chunking them into smaller pieces, and then combine the partial extractions.

B. Increase the max_tokens parameter for the 300 failed documents and resubmit them in a new batch.

C. Resubmit the entire 10,000-document batch using a model tier with a larger context window.

D. Reprocess the entire batch with prompt caching enabled to reduce the cost of retrying requests with identical system prompts.

正解: A

解説: (PassTest メンバーにのみ表示されます)

質問 12

A legal department requires Claude to answer only when sufficient evidence exists in retrieved documents. What should Claude do if evidence is insufficient?

A. Invent a likely answer.

B. Clearly indicate insufficient information.

C. Increase creativity.

D. Search social media automatically.

正解: B

解説: (PassTest メンバーにのみ表示されます)

質問 13

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.
In addition to your CI pipeline, your organization has enabled Claude's managed Code Review through the Claude GitHub App on this repository, and reviews run automatically on every pull request. Reviews average 18 findings per pull request. Developer feedback reveals three categories of unwanted noise: (1) style and formatting issues already enforced by your linter in CI, (2) findings on automatically generated template code under src/gen/, and (3) rendering- helper patterns that are intentional project conventions but get flagged because they resemble common anti-patterns. Only approximately four findings per pull request are genuine logic bugs.
What is the most effective way to reduce this noise while preserving the detection of genuine issues?

A. Add custom review instructions to a GitHub Actions workflow file, using the action's prompt parameter to suppress duplicate lint findings, ignore generated template code, and apply stricter evidence requirements to rendering-related issues.

B. Add detailed explanations to the project's CLAUDE.md describing which patterns are intentional, that linting is handled separately by CI, and that the src/gen/ directory contains automatically generated template code.

C. Create a REVIEW.md file at the repository root containing skip rules for CI-enforced checks and generated files, together with a verification requirement that rendering-related findings cite a specific line demonstrating incorrect behavior.

正解: C

解説: (PassTest メンバーにのみ表示されます)

質問 14

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 call using a Sonnet-tier Claude model. The release notes are not needed until the following morning, so results have approximately 12 hours of acceptable latency. Your team needs to reduce per-token API cost for this step while keeping the same model and prompts, with no change to the model tier or output quality. Which approach satisfies all these constraints?

A. Switch the summarization calls from the Sonnet-tier model to a Haiku-tier model to take advantage of Haiku's lower per-token rates.

B. Issue the 200 Messages API requests in parallel using concurrent connections, because concurrency lowers the per-token price charged by the API.

C. Concatenate all 200 commit messages into a single Messages API request and have the model return all summaries in one response, because fewer requests always reduce total token cost.

D. Submit the 200 requests to the Message Batches API with unique custom_id values and retrieve the results after the batch finishes, which applies a 50% discount to all input and output tokens.

正解: D

解説: (PassTest メンバーにのみ表示されます)

Anthropic Claude Certified Architect - Foundations - CCAR-F 模擬練習