Weekend Special Sale 75% Discount Offer - Ends in 0d 00h 00m 00s - Coupon code: sale75best

Free Anthropic CCAR-F Practice Exam with Questions & Answers | Set: 3

Questions 21

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.

Testing reveals that when source documents are missing certain specifications, the model fabricates plausible-sounding values to satisfy your schema’s required fields. For example, a document mentioning only dimensions receives a fabricated “weight: 2.3 kg” in the extraction output.

What schema design change most effectively addresses this hallucination behavior?

Options:
A.

Add explicit instructions to the prompt stating “only extract information explicitly stated in the document; use placeholder text for missing values.”

B.

Change fields that may not exist in source documents from required to optional, allowing the model to omit them.

C.

Add a “confidence” field alongside each specification where the model self-reports its certainty, then filter out low-confidence extractions.

D.

Implement semantic validation that verifies each extracted value appears in or can be inferred from the source document text.

Anthropic CCAR-F Premium Access
Questions 22

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?

Options:
A.

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

B.

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.

C.

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.

D.

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

Questions 23

The automated review consistently flags patterns your team uses intentionally—force-unwrapping optionals in test files, using large coordinator classes that follow your established architecture, and importing internally maintained modules marked as deprecated in the public SDK. Developers are dismissing approximately 30% of all findings as project-specific false positives. Which approach prevents the model from generating these findings in the first place by supplying the project’s conventions as persistent context during every review?

Options:
A.

Build post-processing keyword filters that suppress findings containing terms such as “force unwrap,” “large class,” or “deprecated import” before results reach developers.

B.

Configure the review to analyze only the changed lines in the diff without surrounding file context, reducing the amount of code the model evaluates during each review.

C.

Have developers add inline suppression comments at flagged lines and preprocess diffs to exclude suppressed lines before sending code to the model.

D.

Document the team’s accepted patterns and intentional conventions in the project’s CLAUDE.md file so the model receives this context during every review.

Questions 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 parses e-commerce product descriptions to extract specifications such as dimensions, weight, and materials into JSON. Despite having a well-defined schema, the model inconsistently extracts the materials field—sometimes returning “cotton blend,” other times “Cotton/Polyester mix,” and occasionally omitting the field when material information is clearly present in the source.

What is the most effective way to improve extraction consistency?

Options:
A.

Set the temperature to 0 to eliminate randomness and ensure deterministic outputs.

B.

Switch to a more capable model tier because inconsistent extraction indicates insufficient model capability.

C.

Make the materials field required instead of optional in the schema to force the model to always extract a value.

D.

Add few-shot examples showing two or three complete input-output pairs with standardized material-description formats.

Questions 25

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.

After expanding the agent’s MCP tools with delivery-specific capabilities (check_delivery_status, contact_driver, issue_credit, apply_promo_code, update_delivery_address, reschedule_delivery), the total tool count has grown from 4 to 10. Your evaluation suite shows tool selection accuracy has dropped from 88% to 71%. Log analysis reveals the majority of errors involve the agent selecting between semantically overlapping tools—calling issue_credit when process_refund was correct, and calling check_delivery_status when lookup_order already returns the needed data.

Which approach structurally eliminates the semantic overlap identified in the logs as the error source?

Options:
A.

Split the tools across two sub-agents—a “financial resolution” agent with process_refund, issue_credit, and apply_promo_code, and a “delivery operations” agent with the remaining delivery tools—with a coordinator routing between them.

B.

Consolidate semantically overlapping tools—merge issue_credit and process_refund into a single resolve_compensation tool with an action parameter, and fold check_delivery_status into lookup_order with an optional include_tracking flag.

C.

Enable the tool search tool with defer_loading on the six new tools, keeping the original four always loaded, so the agent dynamically discovers specialized tools only when needed.

D.

Add few-shot examples to the system prompt demonstrating correct selection for each ambiguous tool pair, such as showing when issue_credit applies versus when process_refund is appropriate.

Questions 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.

An engineer used Claude Code yesterday to investigate authentication flows in a legacy monolith, building up significant context over a 2-hour session. Today she wants to continue that specific investigation. She’s worked on three other codebases since then and knows the session was named “auth-deep-dive”.

How should she resume?

Options:
A.

Use --session-id with the UUID from yesterday’s session transcript file

B.

Use --continue to pick up where the most recent conversation left off

C.

Start fresh and re-read the same files

D.

Use --resume auth-deep-dive to load that specific session by name

Questions 27

Your CI pipeline performs security-focused code reviews on approximately 50 pull requests daily, currently costing $150 per day through the synchronous API. Reviews are non-blocking—developers merge after tests pass and address findings in follow-up commits. You are evaluating the Message Batches API because it offers a 50% cost reduction. What factor most determines whether batch processing is appropriate for this use case?

Options:
A.

Whether your result-processing system can handle reviews arriving in a different order from the order in which they were submitted.

B.

Whether each review can be structured as a single request without multi-turn refinement.

C.

Whether review feedback arriving up to 24 hours after pull-request creation remains actionable.

D.

Whether reducing per-review latency from 30–60 seconds to near-instantaneous delivery matters to your workflow.

Questions 28

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?

Options:
A.

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

B.

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

C.

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

D.

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

Questions 29

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 has been operating with 100% human review for 3 months. Analysis shows that extractions with model confidence ≥90% have 97% accuracy overall. To reduce reviewer workload, you plan to automate high-confidence extractions.

Before deploying, what validation step is most critical?

Options:
A.

Analyze accuracy by document type and field to verify high-confidence extractions perform consistently across all segments, not just in aggregate.

B.

Compare accuracy at different confidence thresholds (85%, 90%, 95%) to find the optimal cutoff that maximizes automation while minimizing errors.

C.

Verify that 97% accuracy meets requirements for all downstream systems that consume the extracted data.

D.

Run a two-week pilot routing 25% of high-confidence extractions directly to downstream systems and monitor error reports.

Questions 30

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?

Options:
A.

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

B.

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

C.

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

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.

Exam Code: CCAR-F
Certification Provider: Anthropic
Exam Name: Claude Certified Architect – Foundations
Last Update: Nov 21, 2026
Questions: 156