Anthropic CCAR-F Exam Overview:

Anthropic CCAR-F Exam Syllabus Topics:

Anthropic Claude Certified Architect – Foundations Sample Questions:

1. 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.
Your team wants Claude to follow a detailed code review checklist (8 items covering API changes, test coverage, documentation, security, etc.) when reviewing pull requests. The team also uses Claude extensively for other tasks: writing new features, debugging production issues, and generating documentation. Currently, developers paste the checklist at the start of each review session.
Which approach best addresses this workflow need?

A) Add the checklist to the project's CLAUDE.md file under a "Code Review" section.
B) Create a dedicated review subagent with the checklist embedded in its configuration.
C) Create a /review slash command containing the checklist, invoked when starting reviews.
D) Configure plan mode as the default for code review sessions.

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.
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) Upgrade to a more capable model tier with improved instruction-following to reduce hallucination tendencies.
C) Add a post-processing step using a second LLM call to verify each extracted value exists in the source document.
D) Make all schema fields required (non-nullable) with strict validation rules to ensure the model only outputs verifiable data.

3. 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.
Production logs show that when the agent handles complex billing disputes requiring 6+ tool calls, it sometimes exhausts its max_turns limit after gathering data but before completing resolution or escalating.
The team's goal is to guarantee that every customer interaction ends with either a completed resolution or a human handoff, regardless of how the agent loop terminates.
Which approach achieves this guarantee?

A) Add system prompt instructions telling the agent to call escalate_to_human with a summary of its findings whenever it determines it cannot complete resolution within its remaining actions.
B) Split the workflow into two sequential agent invocations-a first agent gathers information via get_customer and lookup_order, then a second agent receives that data and handles process_refund or escalate_to_human, each with separate turn budgets.
C) Add orchestration-layer code that checks the agent's outcome after each loop termination-if the loop ended without a completed resolution or escalation, programmatically call escalate_to_human with the accumulated conversation context and tool results.
D) Implement a pre-tool-use hook that counts tool invocations and terminates the loop with an automatic escalation once the agent reaches 80% of its max_turns limit.

4. 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.
Anthropic's tool use documentation states: "Write instructive error messages. Instead of generic errors like
'failed', include what went wrong and what Claude should try next." A billing dispute agent uses lookup_order , which catches all exceptions and returns a tool_result with is_error: true and the message
"Tool execution failed". Monitoring shows two failure modes: the agent retries the identical call until hitting the turn limit, or it immediately calls escalate_to_human without trying alternative tools.
Which change follows the documented recommendation and gives Claude the information it needs to select the correct recovery action for each error type?

A) Remove is_error: true and return the error details as normal tool content, so Claude reasons about the response as data rather than treating it as a flagged failure condition that biases retry behavior.
B) Return error-type-specific messages with is_error: true , e.g., "Order not found-try get_customer to search by phone" for data errors and "Database timeout (transient)-retry should succeed" for infrastructure errors.
C) Implement retry logic with exponential backoff inside each tool implementation so transient errors are resolved transparently within the tool before any failure result is surfaced to Claude in the agentic loop.
D) Add an error classification step in the agentic loop that intercepts tool errors before Claude sees them, then routes to hardcoded retry or escalation logic.

5. 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've asked Claude Code to build a PDF report generation feature. The initial implementation queries the database correctly, but the output has formatting issues: table columns are too narrow causing content truncation, dates display without proper formatting, and page break handling is incorrect. You've noticed these issues interact-changing column widths affects how dates render, and page breaks depend on content height.
What's the most effective approach for iterating toward a working solution?

A) Provide all three issues in a single detailed message with exact specifications for each, allowing Claude to address them together in one update.
B) Address the column width issue first with specific measurements, verify it works, then fix date formatting within the corrected columns, then adjust page breaks-testing after each change.
C) Show Claude an example of a correctly formatted report and ask it to match that output, rather than listing the specific technical issues.
D) Start fresh with a detailed prompt specifying all formatting requirements upfront.

Solutions: