Anthropic CCAR-F real exam prep : Claude Certified Architect - Foundations

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?

• A. Start fresh and re-read the same files
• B. Use --session-id with the UUID from yesterday's session transcript file
• C. Use --resume auth-deep-dive to load that specific session by name
• D. Use --continue to pick up where the most recent conversation left off

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 extraction pipeline processes invoices and extracts line items, subtotals, tax amounts, and grand totals. During evaluation, you discover that in 18% of extractions, the sum of extracted line item amounts doesn't match the extracted grand total--sometimes due to OCR errors in the source document, sometimes due to extraction mistakes by the model. Downstream accounting systems reject records with mismatched totals.
What's the most effective approach to improve extraction reliability?

• A. Add few-shot examples demonstrating invoices where extracted line items sum correctly to the stated total, encouraging the model to produce mathematically consistent extractions.
• B. Implement post-processing that automatically adjusts line item amounts proportionally when their sum doesn't match the stated total.
• C. Extract line items and totals independently, then use a separate validation model to reconcile discrepancies by determining which extracted values are most likely correct.
• D. Add a "calculated_total" field where the model sums extracted line items alongside a
  "stated_total" field. Flag records for human review when values differ.

You are building a structured data-extraction system using Claude. The system extracts information from unstructured documents, validates output against JSON schemas, and integrates the results with downstream systems.
Monitoring reveals that specifications sometimes appear inconsistently within source documents.
For example, a summary section might state "Battery: 4000 mAh," while the detailed specifications table states "Battery: 4200 mAh." Your current schema contains a single battery_capacity field.
This inconsistency occurs in approximately 15% of documents, and historical analysis confirms that the detailed specifications table is accurate 90% of the time.
What is the most effective approach?

• A. Reject every extraction containing conflicting values and require the source document to be corrected before processing continues.
• B. Change the field to an array that captures every discovered value and its source location, leaving downstream systems to apply precedence rules.
• C. Add a conflict_detected Boolean field and route every affected document for manual review.
• D. Add extraction instructions specifying that values from the detailed specifications table take precedence when conflicting values exist, while retaining the single-value schema.

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.
Monitoring shows 12% of extractions fail Pydantic validation with specific errors like "expected float for quantity, got `2 to 3'". Retrying these requests without modification produces identical failures.
What's the most effective approach to recover from these validation failures?

• A. Implement a secondary pipeline using a larger model tier to reprocess documents that fail validation.
• B. Set temperature to 0 to eliminate output variability and ensure consistent formatting.
• C. Pre-process source documents to standardize problematic formats before sending them for extraction.
• D. Send a follow-up request including the validation error, asking the model to correct its output.

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 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.
• B. 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.
• C. 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.
• D. 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.