Anthropic Claude Certified Architect - Professional - CCAR-P

You are preparing an operational runbook for a Claude-based service.
Which content is essential to include in the runbook?

• A. Common alerts and their triage steps, escalation paths, rollback procedures, and references to the relevant dashboards and logs.
• B. Dashboard and log references only, without alert definitions, triage steps, escalation paths, or rollback procedures for the on-call engineer to act on.
• C. Alert definitions and triage steps only, without escalation paths, rollback procedures, or references to dashboards and logs for on-call use.
• D. Escalation paths and rollback procedures only, without alert definitions, triage steps, or dashboard references to guide initial incident response.

You are selecting the documentation set that should accompany a Claude-based deployment at handoff.
Which set is most complete?

• A. A verbal handover walkthrough conducted on the day of transition, with no written architecture overview, ADRs, runbooks, playbook, or known limitations captured for future reference.
• B. Code comments scattered across individual source files with no integrating architecture overview, no ADRs, no runbooks, and no on-call playbook to orient operators or new team members.
• C. Architecture overview, ADRs, component-level diagrams, runbooks for common operations, an on-call playbook, and a list of known limitations.
• D. A single one-page architecture diagram with no ADRs, no runbooks, no on-call playbook, and no list of known limitations to support operators or future maintainers.

A loan pre-qualification assistant shows 94 percent approval recommendations that match the human underwriter decision. The fairness team has reviewed approval rate parity across protected groups and reported no significant difference. A board member has asked whether this evidence is sufficient to declare the assistant fair.
Which two Discernment-competency findings should you report? (Select two.) Each correct answer presents part of the solution.

• A. A larger sample is needed before any meaningful fairness claim can be made about the model.
• B. The 94 percent match rate is sufficient evidence of fairness for the assistant's decisions.
• C. Match with human underwriters does not establish freedom from underwriter-introduced bias.
• D. The fairness team's review process likely missed at least some of the protected groups studied.
• E. Approval rate parity does not by itself assess error rate parity across protected groups.

You are running a discovery session with a business sponsor who asks for "an AI system to fix our customer escalations." Which approach best yields actionable requirements?

• A. Defer the discovery session indefinitely on the grounds that the sponsor must fully specify the system before the architect can ask any clarifying or scoping questions.
• B. Accept the sponsor's original phrasing as a complete and final requirement and proceed directly to design without asking targeted questions to surface actors, triggers, or constraints.
• C. Assume the requirement matches the architect's previous engagement in a different industry and proceed with that context, without validating actors, triggers, or constraints for this sponsor.
• D. Decompose the request by asking targeted questions about who escalates, what triggers escalation, what good resolution looks like, and which constraints-latency, cost, audit, and data sensitivity-apply.

You are comparing patterns for a batch document-classification job that follows fixed steps: extract metadata, classify, summarize, and persist.
Which pattern is the best fit and why?

• A. A workflow pattern, because the steps are well-defined and predictable per-request token cost is preferred over flexibility.
• B. An agentic pattern, because the open-ended planning capability of agents produces more consistent structured outputs than a fixed workflow graph on classification tasks.
• C. An agentic pattern, because agents are categorically more accurate than workflows and therefore always preferable regardless of step predictability.
• D. A workflow pattern, because agentic patterns do not support tool invocations and therefore cannot execute the persist step that writes results to the downstream store.