Anthropic CCA-F 試験概要:

Anthropic CCA-F 試験シラバストピック:

Anthropic Claude Certified Architect Foundations (CCA-F) 認定 CCA-F 試験問題：

問題 #1
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?

A. Index all agent outputs in a shared vector store. When resuming, each agent queries the store using semantic search to retrieve relevant prior findings.
B. 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.
C. Have each agent maintain its own persistent state file and reload it independently at the start of each session.
D. Persist the coordinator's conversation log containing all task delegations and responses, providing this to agents when resuming.

問題 #2
The coordinator provides detailed step-by-step instructions to the web search subagent, specifying exact search queries, source priorities, and date filters. Production monitoring reveals three issues: (1) the subagent reports "insufficient results" rather than trying alternative approaches when pre-specified searches fail, (2) research quality drops for emerging topics that don't match expected patterns, and (3) the subagent rarely surfaces valuable tangential sources.
What's the most effective way to improve subagent adaptability?

A. Specify research goals and quality criteria (coverage breadth, source diversity, recency) rather than procedural steps, letting the subagent determine its search strategy.
B. Remove procedural details entirely, delegating with simple goals like "research X thoroughly" and relying on the subagent's general capabilities.
C. Add explicit fallback directives to the detailed instructions: "If specified searches yield fewer than N results, attempt alternative query formulations before reporting failure."
D. Implement a topic classification step where the coordinator categorizes requests as "well-defined" or "exploratory" and uses different instruction styles for each category.

問題 #3
What is the PRIMARY purpose of few-shot prompting?

A. Increase model size.
B. Reduce token costs.
C. Encrypt prompts.
D. Demonstrate desired output patterns.

問題 #4
In production, final reports frequently contain claims without proper source attribution.
Investigation shows that while the web search and document analysis agents correctly attach citations to their outputs, the synthesis agent loses track of which sources support which conclusions when combining findings. What's the most effective architectural change?

A. Require all subagents to output structured claim-source mappings that the synthesis agent must preserve and merge when combining findings from multiple sources.
B. Add a verification step where the report generator uses semantic similarity matching against original sources to reconstruct which claims came from which documents.
C. Maintain complete transcripts of all subagent interactions and add a citation-resolution agent to analyze logs and determine attributions before report generation.
D. Have the coordinator inject source identifier prefixes into text before each handoff, then parse these prefixes at report generation to reconstruct citations.

問題 #5
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?

A. Report error 1 as a JSON-RPC protocol error; report errors 2 and 3 as tool results with isError:
true.
B. Report all three as JSON-RPC protocol errors.
C. Report all three as tool results with isError: true.
D. Report errors 1 and 2 as JSON-RPC protocol errors; report error 3 as a tool result with isError:
true.

解説：