Anthropic CCA-F 시험 개요:

Anthropic CCA-F 시험 요강 주제:

최신 Claude Certified Architect CCA-F 무료샘플문제

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

A) Remove formatting instructions.
B) Increase randomness.
C) Specify exact column names.
D) Omit examples.

2. A customer returns 4 hours after the initial session about the same billing dispute. The previous
32-turn session contains lookup_order results showing "Status: PENDING, Expected resolution:
24-48 hours." In testing, you observe that when resuming sessions with stale tool results, the agent often references the outdated data in responses (e.g., "I see your refund is still being processed") even after subsequent fresh tool calls return different information. What approach most reliably handles returning customers?

A) Resume with full history and configure the agent to automatically re-call all previously-used tools at session start to ensure data freshness.
B) Resume with full history and add a system prompt instruction telling the agent to always prefer the most recent tool results when multiple calls to the same tool exist in context.
C) Resume with full history but filter out previous tool_result messages before resuming, keeping only the human/assistant turns so the agent must re-fetch needed data.
D) Start a new session, inject a structured summary of the previous interaction (issue type, actions taken, resolution status), then make fresh tool calls before engaging.

3. 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) 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 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.
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. A team wants to reduce hallucinations without significantly changing application logic. Which improvement should be implemented FIRST?

A) Add reliable retrieval sources.
B) Raise temperature.
C) Shorten all outputs.
D) Remove role instructions.

5. An architect needs Claude to produce structured JSON that downstream software can parse automatically. Which prompting strategy is BEST?

A) Ask Claude to "respond normally."
B) Use multiple unrelated examples.
C) Explicitly specify the required JSON schema and formatting rules.
D) Increase maximum output tokens only.

질문과 대답: