2026年11月最新のAnthropic CCAR-F問題集で更新された191問あります [Q21-Q38]

4/5 - (1 vote)

2026年11月最新のAnthropic CCAR-F問題集で更新された191問あります

PDF無料ダウンロードにはCCAR-F有効な練習テスト問題

Anthropic CCAR-F 試験シラバストピック:

セクション	比重	目標
コンテキスト管理と信頼性	15%	– コンテキスト処理 1. メモリ戦略 2. コンテキストウィンドウ管理 3. コストとパフォーマンスの最適化 4. 信頼性と評価
Claude Codeの設定とワークフロー	20%	– Claude Code 1. 設定とプロジェクトのセットアップ 2. コード生成と自動化 3. 開発ワークフロー 4. エージェントスキル
ツール設計とMCP統合	18%	– ツール統合 1. リソースとサーバーの統合 2. Model Context Protocol (MCP) 3. ツールインターフェース設計 4. ツールの選択と安全性
プロンプトエンジニアリングと構造化出力	20%	– プロンプトデザイン 1. 構造化出力とJSONスキーマ 2. プロンプトエンジニアリング手法 3. Few-shotプロンプト 4. 出力の検証
エージェントアーキテクチャとオーケストレーション	27%	– エージェントアーキテクチャパターン 1. ワークフロー設計 2. シングルエージェントおよびマルチエージェントアーキテクチャ 3. 計画および実行戦略 4. エージェントオーケストレーション

質問 21
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 automated review jobs take 18 seconds to initialize before Claude begins analyzing code. Profiling reveals that the delay results from automatically discovering hooks, MCP servers, plugins, skills, and multiple nested CLAUDE.md files throughout the monorepo.
You need to reduce startup time while ensuring reviews still enforce the coding standards documented in the root-level CLAUDE.md file.
What is the most effective approach?

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

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

Run in –bare mode and repeat all review criteria directly in the -p prompt for every invocation.

Keep the default initialization and add –exclude-dynamic-system-prompt-sections to improve prompt- cache reuse across CI runners.

質問 22
Your pipeline runs:
PROMPT=”You are a code reviewer.”
PROMPT=”$PROMPT Analyze the provided diff”
PROMPT=”$PROMPT for bugs, security issues,”
PROMPT=”$PROMPT and style violations.”
claude -p
–dangerously-skip-permissions
–system-prompt “$PROMPT” < diff.txt
The reviews complete and return feedback, but Claude comments only on the piped diff–it never reads surrounding files in the checked-out repository to understand broader context, even when the diff modifies a function called by many other modules. Which change to the invocation will cause Claude to read related repository files while still applying your custom review instructions?

Keep –system-prompt and add –allowedTools “Read, Glob, Grep” because non-interactive -p mode otherwise disables filesystem tools.

Replace –system-prompt with –append-system-prompt so the review instructions are added to Claude Code’s default prompt instead of overwriting its built-in file-reading and code-navigation guidance.

Remove –system-prompt entirely and place the review instructions in a root-level CLAUDE.md because –system-prompt is incompatible with tool use under -p.

Stop piping the diff through standard input and embed it in the prompt string so Claude Code treats the invocation as an agentic session rather than a stream-processing operation.

質問 23
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 analyzing complex legal cases that cite multiple precedents, the document-analysis subagent processes each precedent sequentially. A landmark case citing 12 precedents takes more than three minutes to analyze completely.
What is the most effective way to reduce this latency while preserving the coordinator’s ability to monitor and debug the system?

Implement a message queue where precedent-analysis tasks are processed asynchronously by a pool of worker agents.

Enable the document-analysis subagent to spawn its own specialized subagents dynamically when it encounters cases with many citations.

Have the coordinator spawn parallel document-analysis subagents, each handling a subset of precedents, and then aggregate the results before synthesis.

Create a recursive agent hierarchy where analysis agents subdivide work among child agents until reaching single-precedent granularity.

質問 24
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?

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.

Route standard reports to the Message Batches API for 50% cost savings, and route urgent exception reports to the real-time Messages API.

Queue all documents and submit hourly batches, flagging urgent documents for expedited handling when batch results return.

Submit all documents to the real-time Messages API to ensure consistent processing latency across document types.

質問 25
Your automated code review is missing genuine bugs in pull requests. Investigation reveals that the review prompt includes this instruction: “Only flag critical issues that would definitely cause production failures.
Ignore minor concerns and anything you are uncertain about.” Developers confirm that some missed findings are genuine logic errors that the model investigated but chose not to report. The team requires the review output to remain structured, with every finding tagged with metadata, and actionable. Which prompt change both removes the cause of the suppressed findings and preserves structured, tagged output for downstream filtering?

Enable extended thinking and instruct the model to reason step by step about every code change before producing its review.

Instruct the model to report all findings with confidence and severity tags, deferring filtering to a downstream step.

Remove all severity-related instructions and allow the model to use its default judgment about which findings to report.

Add a second review pass that rereads the diff using the same prompt and looks for anything the first pass may have missed.

質問 26
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.
Your code review assistant needs to analyze pull requests and provide feedback on three aspects: code style compliance, potential security issues, and documentation completeness. Each aspect requires reading files, running analysis tools, and generating a report section. The review process follows the same three-step workflow for every PR.
Which task decomposition pattern is most appropriate for this workflow?

Single comprehensive prompt-include all three instructions in one prompt and let the model handle all three aspects simultaneously.

Orchestrator-workers-have a central LLM analyze each PR to dynamically determine which checks are needed, then delegate to specialized worker LLMs for each identified subtask.

Prompt chaining-break the review into sequential steps where each aspect (style, security, documentation) is analyzed separately, with outputs combined in a final synthesis step.

Routing-classify each PR by type (feature, bugfix, refactor) first, then route to different review prompts optimized for that category.

質問 27
The synthesis agent completes its initial pass but flags that three key research questions remain unanswered because the web search and document analysis agents didn’t find relevant information on those specific subtopics. The coordinator currently proceeds directly to report generation, producing reports with incomplete coverage. What change would most effectively improve research completeness?

Have the report generation agent note which research questions couldn’t be answered, so users understand the limitations of the final output.

Increase the initial breadth of queries sent to web search and document analysis to reduce the probability of missing relevant information.

Have the coordinator evaluate synthesis output for gaps, then re-delegate to web search and document analysis with targeted queries before invoking synthesis again.

Give the synthesis agent direct access to web search tools so it can autonomously fill knowledge gaps without returning control to the coordinator.

質問 28
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.
An engineer asks your agent to add comprehensive tests to a legacy codebase with 200 files and minimal existing test coverage. The engineer hasn’t specified which modules to prioritize.
How should the agent decompose this open-ended task?

Create a fixed testing schedule upfront based on directory structure, allocating equal effort to each top-level directory regardless of code complexity or business importance.

Use Glob and Grep to map codebase structure, identify heavily-coupled modules, create a prioritized plan for high-impact areas, and revise as dependencies are discovered.

Systematically read all 200 files to create a complete function inventory before writing any tests, ensuring the testing plan accounts for every function before beginning.

Start writing tests for the first module alphabetically, using test failures and imports to discover related files organically.

質問 29
You are building a customer support resolution agent using the Claude Agent SDK. The agent handles high- ambiguity requests like returns, billing disputes, and account issues. It has access to your backend systems through custom Model Context Protocol (MCP) tools ( get_customer , lookup_order , process_refund , escalate_to_human ). Your target is 80%+ first-contact resolution while knowing when to escalate.
When the agent calls lookup_order and receives order details showing the item was purchased 45 days ago, how does the agentic loop determine whether to call process_refund or escalate_to_human next?

The order details are added to the conversation and the model reasons about which action to take.

The orchestration layer automatically routes to the next tool based on the order’s status field.

The agent follows a pre-configured decision tree mapping order attributes to specific tool calls.

The agent executes the remaining steps in a tool sequence planned at the start of the request.

質問 30
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.
A developer asks the agent to investigate why a specific API endpoint intermittently returns 500 errors. The codebase has 200+ files and the developer doesn’t know which components are involved. The agent must trace the error through routing, middleware, business logic, and database layers.
What task decomposition approach would be most effective?

Have the agent first create a comprehensive plan mapping all code paths through the endpoint before beginning any file exploration or code reading.

Define a fixed sequence of investigation steps upfront-grep for error patterns, then read error handlers, then check database queries, then examine middleware-executing each step regardless of intermediate findings.

Run parallel worker agents that simultaneously investigate all four layers, then synthesize their findings to identify where the error originates.

Have the agent dynamically generate investigation subtasks based on what it discovers at each step, adapting its exploration plan as new information about the error path emerges.

質問 31
Your multi-agent research pipeline crashed after processing12 of 28 documents. The web search agent had identified relevant sources, the document analyzer had partially completed extraction, and the synthesizer had begun pattern identification. You need to resume processing without repeating work or losing fidelity of prior findings. What state management approach best balances information fidelity with context efficiency when restoring agent state?

Have each agent persist a structured export to a known location. On resume, the coordinator loads the manifest and injects relevant state into agent prompts.

Index all agent outputs in a shared vector store. When resuming, each agent queries the store using semantic search to retrieve relevant prior findings.

Have each agent maintain its own persistent state file and reload it independently at the start of each session.

Persist the coordinator’s conversation log containing all task delegations and responses, providing this to agents when resuming.

質問 32
Your MCP server implements a check_availability tool that queries an external calendar API.
During testing, you encounter three error conditions: (1) the tool is called with a malformed request missing the required user_email parameter, (2) the calendar API returns a 404 because the specified user doesn’t exist in the calendar system, and (3) the calendar API returns a 503 because the service is temporarily unavailable. How should each error be reported according to MCP’s error handling design?

Report all three as tool results with isError: true.

Report errors 1 and 2 as JSON-RPC protocol errors; report error 3 as a tool result with isError:
true.

Report error 1 as a JSON-RPC protocol error; report errors 2 and 3 as tool results with isError:
true.

Report all three as JSON-RPC protocol errors.

質問 33
When implementing your lookup_order MCP tool, the backend sometimes returns errors (e.g.,
“Order not found” or temporary database failures). What is the correct pattern for communicating these errors back to the agent?

Throw an exception from the tool handler so the agent framework can catch and log it

Return the error message in the tool result content with the isError flag set to true

Log the error server-side and return an empty result to avoid confusing the model

Return a success response with a “status” field indicating the error type

質問 34
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 must extract event details from calendar invitations and output JSON that strictly conforms to a schema with fields for title, date, time, location, and attendees. Downstream systems reject any malformed or non-conformant JSON.
What approach provides the most reliable schema compliance?

Pre-fill Claude’s response with an opening brace to force JSON output, then complete and parse the response.

Append instructions like “Output only valid JSON matching the schema exactly” and implement retry logic to re-prompt when JSON parsing fails.

Define a tool with your target schema as input parameters and have Claude call it with the extracted data.

Include detailed JSON formatting instructions and the target schema in your prompt, then parse Claude’s text response as JSON.

質問 35
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?

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

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

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

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

質問 36
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.
An engineer’s exploration subagent spent 30 minutes analyzing a legacy payment system, reading 47 files and documenting data flows. The session was interrupted when the engineer’s connection dropped. While away, a teammate merged a PR that renamed two utility functions.
The engineer wants to continue the same exploration.
What’s the most effective approach?

Launch a fresh subagent with a summary of prior findings.

Resume the subagent from its previous transcript without mentioning the changes–the architecture understanding remains valid.

Resume the subagent from its previous transcript and inform it about the renamed functions.

Launch a fresh subagent and include the prior transcript in the initial prompt for context.

質問 37
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 automated review jobs take 18 seconds to initialize before Claude begins analyzing code.
Profiling reveals that the delay results from automatically discovering hooks, MCP servers, plugins, skills, and multiple nested CLAUDE.md files throughout the monorepo.
You need to reduce startup time while ensuring reviews still enforce the coding standards documented in the root-level CLAUDE.md file.
What is the most effective approach?

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

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

Run in –bare mode and repeat all review criteria directly in the -p prompt for every invocation.

Keep the default initialization and add –exclude-dynamic-system-prompt-sections to improve prompt-cache reuse across CI runners.

質問 38
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 uses tool use with a JSON schema containing 12 fields and detailed descriptions, totaling approximately 2,500 tokens for the complete tool definition. Processing documents under 150,000 tokens yields 98% accuracy. For documents between 175,000 and
190,000 tokens, accuracy drops to 71%, with information from the final third consistently missed.
The model’s context window is 200,000 tokens.
What is the most likely cause?

Schemas exceeding eight to ten fields increase decision complexity during parameter generation, reducing extraction accuracy independently of document length.

The model distributes attention proportionally across the input length, causing fields mentioned only once near the document’s end to receive insufficient processing focus.

Very long documents exceed the model’s effective attention span regardless of context limits, causing accuracy degradation for content farther from the prompt instructions.

Tool definitions consume input-context tokens. Combined with system prompts and document content, the total approaches the context limit, degrading end-of-document processing.