CCAR-P Sample Questions Answers

Option B targets two major contributors to per-turn latency: retrieved-context size and repeated prompt processing. Reducing retrieval to an empirically validated top-k limits the tokens Claude must process while preserving the passages that historically provide sufficient answer coverage. Caching the stable system-prompt prefix avoids repeatedly processing identical instructions.

Anthropic’s latency guidance recommends choosing an appropriate model and reducing unnecessary input and output tokens. Its prompt-caching documentation explains that caching reusable prompt prefixes can reduce both repeated processing cost and latency. Reducing Latency, Prompt Caching

The retrieval depth must be selected through evaluation rather than arbitrary truncation. The team should compare answer quality, retrieval recall, latency, and failure rates across candidate values and retain escalation logic for complex queries requiring deeper retrieval.

Option A removes an applicable latency optimization. Option C maximizes context consumption regardless of demonstrated benefit. Option D deliberately selects the slowest model class even though routine-turn quality already meets requirements.

Study Guide references/topics: Latency optimization; top-k retrieval; prompt caching; token reduction; quality–latency evaluation; adaptive retrieval.

===============

Responsible deployment requires users to receive an accurate representation of the system with which they are interacting. Option C provides that transparency while also establishing a practical escalation path. Disclosure should be proportionate to the material role AI plays, expressed in language appropriate to the audience, and aligned with organizational policy and applicable regulatory obligations.

A documented human-contact route is important when the assistant cannot resolve an issue, produces a disputed result, encounters a high-impact exception, or handles a matter requiring human authority. Anthropic’s Responsible Scaling Policy recognizes escalation to human reviewers as an appropriate safeguard for edge cases and situations requiring human judgment. Responsible Scaling Policy

Options A and D intentionally conceal material AI involvement from affected users, weakening informed decision-making, auditability, and trust. Option B is also unsuitable because transparency does not require revealing proprietary prompts, confidential controls, or internal security mechanisms; however, it does require an honest explanation of AI involvement and the system’s operational role.

The correct design combines disclosure, understandable limitations, human escalation, and records demonstrating that the organization’s transparency requirements are consistently applied.

Study Guide references/topics: AI transparency; informed user interaction; human escalation; responsible deployment; disclosure policy; operational accountability.

===============

Authorization must be enforced before restricted information enters model context. The retrieval service should authenticate the user, resolve role and document permissions, and filter candidate records before prompt construction. This prevents unauthorized content from appearing in prompts, model traces, cached context, tool results, or generated responses. A system-prompt instruction is behavioral guidance, not an enforceable access-control boundary. Post-generation filtering is also inadequate because the model has already received and processed the restricted data, creating exposure through output, logging, or indirect inference. Relying on general refusal behavior provides no deterministic authorization. The correct architecture treats RBAC as an application and data-layer control, with the model receiving only information the requesting principal is entitled to access.

Study Guide references/topics: Retrieval-layer RBAC; authorization before inference; least privilege; sensitive-context isolation.

Strong decision communication must explain both how the decision was reached and how it will remain governed. Option D provides the reasoning structure: the alternatives considered and the criteria used to compare them. This allows reviewers to verify that capability, cost, latency, security, maintainability, integration complexity, and business outcomes were evaluated consistently rather than selectively.

Option A establishes lifecycle accountability. Architectural decisions depend on assumptions about requirements, models, data, regulations, usage volume, and operational constraints. Naming an owner and review cadence ensures the decision is reconsidered when those assumptions materially change.

Option B imposes a meeting mechanism rather than describing decision quality. Mandatory attendance by senior leaders may add delay without improving the clarity or correctness of the record. Option C removes important evidence and increases the chance that rejected approaches will be proposed again without addressing the original objections. Option E can improve consistency and discoverability, but visual standardization alone does not establish substantive architectural communication.

A strong decision record should therefore be evidence-based, audience-accessible, traceable to requirements, explicit about alternatives and consequences, assigned to an accountable owner, and governed by defined review triggers.

Study Guide references/topics: Architectural-decision communication; alternatives analysis; evaluation criteria; decision ownership; review cadence; changing assumptions; lifecycle governance.

Observation 1 is a direct efficiency improvement because the time required for one summarization task fell substantially. Observation 2 shows that local time savings have not yet translated into higher organizational productivity or billable output. Observation 3 is explicitly a solution-cost problem caused by unnecessary API calls. Observation 4 introduces additional human correction time and therefore partially offsets the gross efficiency gain reported in Observation 1. Option D is the only answer that keeps these value dimensions distinct. Measuring only generation speed would overstate realized value because review effort, retry costs, and downstream output must also be included. A valid post-deployment assessment should calculate net cycle time, cost per accepted summary, correction rate, and resulting business output.

Empirical model testing requires a defined decision frame. Option D must occur first because the quality threshold, acceptable latency, expected request volume, and associated cost envelope determine what constitutes a successful result. Without these criteria, a representative-sample test can produce measurements but cannot support a defensible selection.

Option C is the next upstream step. Known model capabilities and the workload profile are used to identify a plausible candidate rather than testing models arbitrarily. Anthropic’s model-selection guidance recommends evaluating capability, speed, cost, and effort requirements before narrowing the candidate set. Choosing the Right Model

Option A occurs after empirical testing because the architect cannot know which lightest model consistently meets the quality bar until sample results have been evaluated. Option B belongs to ongoing lifecycle management after a new version becomes available. Option E is a deployment-governance activity that follows successful model selection, security review, and readiness validation.

The correct sequence is: define workload criteria, shortlist candidate models, run a representative evaluation, compare quality and operational metrics, select the least costly model that reliably satisfies all gates, and periodically retest the decision.

Study Guide references/topics: Requirements-driven model selection; representative sampling; quality thresholds; latency and volume requirements; capability–cost trade-offs; model lifecycle reassessment.

===============

Security and compliance reviewers must determine whether material threats have been identified, whether required controls address those threats, how remaining exposure will be accepted, and whether the decision can be demonstrated during an audit. Option C supplies exactly that evidence.

The threat model establishes protected assets, trust boundaries, adversaries, attack paths, and likely failure modes. Control mappings connect technical and procedural safeguards to organizational policies, regulatory requirements, and assurance frameworks. Residual-risk acceptance criteria define which risks may remain after mitigation, who has authority to accept them, and when further treatment is mandatory. Audit traceability connects requirements and decisions to implementation evidence, evaluations, approvals, logs, and operational monitoring.

Option A is designed primarily for product management. Option B addresses engineering planning and execution. Option D is appropriate for an executive sponsor who requires business justification and a concise risk summary but normally does not perform detailed control verification.

Audience adaptation should not alter the architectural decision itself. It changes the depth, terminology, evidence, and ordering used to communicate the decision. Security and compliance reviewers require verifiable control evidence rather than only schedule, implementation, or business-level summaries.

Study Guide references/topics: Audience-specific communication; threat modeling; compliance control mapping; residual-risk acceptance; audit evidence; architectural decision traceability.

===============

Yes, No, Yes, No, Yes

Least privilege requires each retained tool to be necessary for the agent’s assigned responsibility and restricted to the minimum action level needed. Catalog lookup is appropriate because vendor and SKU information is needed to prepare an accurate request. The policy-document tool is similarly justified because the agent must ground the draft in applicable procurement rules. The draft-write tool is also aligned because it writes only to a review queue, preserving the required human approval boundary.

The inbox-send tool exceeds the stated responsibility. Sending a request directly to a vendor converts a drafting assistant into an externally acting purchasing agent and bypasses the review stage. The production-database administrator tool is unrelated to procurement and introduces unnecessary destructive capability, privilege-escalation exposure, and potential data-access risk.

Anthropic’s prompt-injection guidance recommends limiting access to sensitive data and actions and applying least privilege so that a compromised agent can cause minimal damage. Claude Code also supports tool-specific allow, ask, and deny rules that are enforced outside the model. Prompt-Injection Mitigation, Claude Code Permissions

Study Guide references/topics: Capability-bloat auditing; least privilege; tool scoping; human review gates; separation of drafting and execution authority.

===============

Yes, Yes, Yes, No, No

Dense vector retrieval represents semantic similarity, making it suitable for matching paraphrases and conceptually related language even when the query and source do not share identical words. Sparse lexical retrieval, including BM25-style matching, retains strong sensitivity to exact tokens and is therefore valuable for identifiers, product codes, technical names, and uncommon terminology.

Structured query retrieval is appropriate when the required operation depends on explicit fields, predicates, joins, counts, grouping, or aggregation over a relational schema. In that situation, generating or invoking a constrained database query is more precise than approximating the operation through semantic similarity.

Hybrid retrieval is not identical to dense retrieval. It combines semantic and lexical candidate sets, typically followed by rank fusion or reranking. Anthropic’s contextual-retrieval guidance explains that semantic search captures meaning and paraphrases, while BM25 captures exact terminology; combining them improves coverage. Contextual Retrieval, Contextual Retrieval Cookbook

Random sampling is not a relevance strategy. It provides no systematic relationship between the query and selected evidence, producing unstable coverage and preventable hallucination risk. Production Q & A requires deterministic or evaluated relevance mechanisms, access filters, suitable indexes, and measurable retrieval metrics such as recall at k.

Study Guide references/topics: Dense retrieval; sparse retrieval; structured queries; hybrid search; rank fusion; retrieval evaluation; production RAG design.

===============

An Architecture Decision Record is designed to preserve a significant architectural choice in a concise, durable, and reviewable form. The context explains the problem, constraints, and forces that shaped the decision. The decision section records the selected approach. Alternatives demonstrate that other viable options were evaluated, while consequences identify benefits, costs, limitations, operational obligations, and residual risks. The date and authors establish accountability and historical sequence.

This structure supports audit because a reviewer can trace why a model, integration pattern, retrieval architecture, security boundary, or deployment approach was chosen. It also supports onboarding by preventing new team members from interpreting intentional design choices as arbitrary implementation details.

A slide deck may communicate a decision at a meeting but is weak as the sole authoritative record when it lacks written rationale. A code comment is too localized and may not capture system-level implications or rejected alternatives. A verbal conversation creates no durable evidence and depends entirely on individual memory.

The ADR should be version-controlled, linked to affected requirements and implementation artifacts, assigned an owner, and reviewed when its assumptions or operating conditions materially change.

Study Guide references/topics: Architecture Decision Records; decision context; alternatives; consequences; auditability; onboarding; lifecycle review.

===============

The absence of company-specific training does not establish unbiased behavior. A foundation model may reflect demographic associations or unequal treatment patterns originating from pretraining data, model behavior, prompt framing, retrieval content, or the surrounding decision workflow. Because candidate screening can materially affect employment opportunities, the complete system must be evaluated across relevant protected groups before deployment. Appropriate measures include selection-rate differences, false-positive and false-negative rates, calibration, intersectional slices, and human override patterns. Disclosure that AI is used does not replace empirical fairness testing. Protected-class labels need not have been explicit in training data for proxy variables or inferred attributes to produce disparities. Provider policies similarly do not validate a customer’s specific implementation. Anthropic system cards document discriminatory-bias evaluations, reinforcing the need for application-level testing. Claude model system card

A minimal reproduction and MCP status inspection are foundational diagnostic actions because they produce direct, interpretable evidence. A minimal reproduction removes unrelated prompts, tools, settings, hooks, and repository state while changing one variable at a time. This determines whether the failure follows a particular configuration, server, command, model request, or project artifact. It also creates a reproducible evidence package if escalation later becomes necessary.

MCP inspection addresses a common Claude Code failure domain. `claude mcp list` displays configured servers and their health states, including connected, authentication-required, pending-approval, and failed-to-connect conditions. `claude mcp get < name > ` provides server-specific details, while `/mcp` exposes status within an interactive session. These checks distinguish model behavior from transport, authentication, configuration, and workspace-trust failures.

Increasing temperature reduces repeatability and introduces additional variation, making root-cause isolation more difficult. Filing a support ticket before collecting local evidence reverses the appropriate diagnostic sequence. An immediate rollback may eventually be used as a controlled version comparison, but it changes the environment before a baseline has been captured and is therefore not a primary toolkit action.

Study Guide references/topics: [Managing and diagnosing MCP servers](https://docs.anthropic.com/en/docs/claude-code/mcp); minimal reproducible cases; controlled-variable troubleshooting; authentication and connection-state diagnostics.

===============

Architecture X fails a stated production gate: its 4.2-second average exceeds the required three-second response SLA. It should therefore not remain a qualifying architecture unless it is redesigned and retested before selection. A promise to optimize after deployment is not evidence of compliance.

Architecture Y meets the latency requirement at 2.1 seconds. Its annual inference cost is $180,000 at two million sessions, compared with $360,000 for Architecture X—a difference of $180,000 annually. However, cost alone does not establish suitability. The organization must determine whether Y’s lower quality score causes material omissions, correction effort, clinician dissatisfaction, documentation risk, or reduced workflow productivity.

Option C correctly treats the SLA as a threshold and then analyzes the remaining architecture across cost, efficiency, quality, and productivity. Option A ignores clinical quality. Option B disregards an explicit SLA failure. Option D may eventually be viable, but it introduces routing complexity and leaves unanswered how complex cases are detected, whether X’s latency becomes acceptable for them, and how both paths are evaluated.

The final choice should be gated by clinical-quality evaluation, human review requirements, safety metrics, operational latency, and total annual cost.

Study Guide references/topics: Business-value pillars; performance gates; solution cost; workflow efficiency; quality trade-offs; healthcare architecture evaluation.

===============

Credentials must never be supplied as prompt content. Prompts can be retained in traces, debugging output, caches, or logs, and model output may inadvertently expose included secrets. Credentials should instead be resolved server-side through an approved secret store or delegated authentication mechanism. Option C is also a serious gap because post-response RBAC occurs after unauthorized data has already entered model context. Authorization must be enforced before retrieval and prompt construction. Options A, D, and E describe appropriate controls: least-privilege service identities, per-user scoped OAuth, and encrypted transport. Anthropic’s prompt-leak guidance recommends excluding unnecessary sensitive information, while Claude Code security relies on permission-based enforcement rather than natural-language instructions alone. Reduce prompt leak

A structured feedback session must enable informed review, traceable decisions, and accountable follow-through. Option B allows stakeholders to examine architecture diagrams, evaluation results, risk registers, or prototypes before the meeting. The focused agenda keeps discussion aligned with decisions that must be made rather than allowing the session to become an unstructured status conversation. Written decision records prevent different participants from leaving with incompatible interpretations. Assigning an owner and due date to every action converts feedback into executable delivery work. Options A, C, and D depend heavily on memory, provide inadequate preparation time, and create weak decision traceability. In-flight deployments particularly require documented feedback because accepted changes may affect scope, cost, risk, testing, and release timing.

Study Guide references/topics: Stakeholder feedback; decision records; action ownership; lifecycle alignment; communication planning.

Haiku is the appropriate starting point because the workload is high-volume, latency-sensitive, and based on a stable closed set of moderation labels. These characteristics favor a fast, cost-efficient model capable of consistent classification without incurring the additional inference time and expense associated with deeper reasoning.

Anthropic’s model-selection guidance requires architects to balance capability, speed, and cost rather than automatically selecting the most capable model. Its content-moderation guidance specifically identifies Haiku as a cost-effective option for processing moderation workloads at substantial scale. Choosing the Right Model, Content Moderation

Opus is disproportionate to a routine closed-set classification problem. Sonnet may become justified if evaluation demonstrates that Haiku fails materially on complex policy distinctions, multilingual ambiguity, or adversarial edge cases, but it should not be selected merely because it is larger. Enabling extended thinking on every request would further increase latency and token consumption without evidence that the additional reasoning improves the defined success metrics. The correct architectural practice is to establish a representative moderation evaluation set, validate Haiku against accuracy and safety thresholds, and escalate only the cases that genuinely need deeper reasoning.

Study Guide references/topics: Model selection; capability–latency–cost trade-offs; classification workloads; evaluation-driven routing; moderation architecture.

===============

A clearly defined closed-set classification task should begin with a concise zero-shot prompt containing the permitted categories, unambiguous category descriptions, and the required output structure. This provides a simple, inexpensive baseline that can be measured against a representative evaluation set. Chain-of-thought prompting adds unnecessary latency and token usage when the routing decision does not require substantive multi-step reasoning. Permitting Claude to invent categories would violate the closed-set contract and complicate downstream automation. Omitting descriptions would increase ambiguity among potentially overlapping labels. If evaluation later reveals persistent confusion between particular categories, the architect can introduce targeted examples or refine the definitions. Prompt complexity should be added in response to measured failure patterns, not assumed to be necessary before establishing baseline performance. Anthropic: Prompt engineering overview

================

The pilot must test a deliberately designed workflow, not technology added without role boundaries. Option B identifies where Claude provides measurable value and where approval, accountability, or consequential decisions must remain human responsibilities. Option E establishes the technical environment required for consistent pilot execution: repository-shared MCP servers, scoped permissions, specialized subagents, and persistent project instructions. Iteration in Option D necessarily follows observed pilot findings. Formal approval from every manager is unnecessarily broad unless required by organizational governance. Complete runbooks and final handoff documentation mature after the workflow has been validated, although essential pilot procedures must exist. Anthropic documents project-level instructions, permissions, MCP servers, and subagents as complementary mechanisms for team workflows. Claude Code extension overview

Project-scope configuration is appropriate for shared MCP definitions, permissions, hooks, and other repository-specific behavior that every team member should receive consistently. Managed configuration complements this by enforcing organization-wide security and compliance requirements that individual developers cannot override. Together, these mechanisms separate collaborative project configuration from centrally controlled policy. Editor themes are personal preferences and do not materially establish a secure environment. Allowing each engineer to select an arbitrary model can undermine consistency when model choice affects behavior, cost, or approved-use requirements. Storing a shared API key in a committed project file is a serious credential-management failure. Claude Code documentation identifies .claude/settings.json as the shared project file and managed settings as the highest-precedence organizational policy layer. Claude Code: Settings files and precedence

================

A dedicated subagent is justified when specialization is recurring and operationally valuable. Option A allows the team to encode a database-review role once, including its system prompt, triggering description, permitted tools, model, and review criteria. This improves consistency across sessions, isolates specialized context, and applies least privilege by withholding unrelated capabilities. Anthropic’s custom subagent documentation supports task-specific prompts, model selection, tool allowlists, permission modes, hooks, skills, and persistent memory. A one-time question does not justify the maintenance overhead of a reusable agent definition, while Options C and D explicitly provide no specialization requirement. The subagent should also have clear invocation conditions, evaluation cases, ownership, and lifecycle review.

Study Guide references/topics: Claude Code subagents; task specialization; context isolation; model routing; scoped permissions; reusable automation.

Statement 1 measures efficiency because the same operating unit—one procurement analyst—now processes three times as many purchase orders per day. It reflects increased throughput and reduced effort per transaction within the existing procurement process.

Statement 2 represents transformation. The organization has not merely accelerated manual data entry; it has eliminated that role from the workflow and redirected employees toward higher-value vendor relationship management. This is a structural redesign of responsibilities and operating practices.

Statement 3 is a solution-cost issue because the measured API integration expense exceeds the approved per-transaction financial model by 40%. The architect must investigate token consumption, model routing, caching, retrieval overhead, tool calls, and integration charges while protecting the required quality level.

Statement 4 directly concerns the performance SLA. The observed 11-second latency is compared with an explicit contractual or operational target of five seconds. This is not simply an efficiency complaint; it is a measurable breach of a defined service-level commitment.

The architect should map each stakeholder statement to its dominant value pillar before recommending remediation because throughput, organizational transformation, cost control, and SLA compliance require different architectural responses.

Study Guide references/topics: Business-value pillars; efficiency; transformation; solution cost; performance SLAs; stakeholder-outcome classification.

===============

High-impact AI-supported decisions must retain clearly assigned human accountability. Claude may provide recommendations, classifications, or generated content, but responsibility for consequential outcomes cannot be transferred to the model. An ethics review should also investigate whether outputs make unsupported generalizations about individuals or groups, because such behavior can produce discriminatory, misleading, or harmful outcomes. Therefore, B and E directly address ethical accountability and fairness. Licensing in option A is an important legal and procurement concern, but it is not the strongest ethics-focused control presented. Latency and throughput in option D are operational performance requirements. Option C is inappropriate because ethics risks are not limited to outputs above a confidence threshold; confidence values may also be poorly calibrated and do not prove that an output is fair, accurate, or ethically acceptable.

================

Yes, Yes, No, Yes, No

Zero-shot prompting is a reasonable baseline for a clearly defined closed-set classifier because the model receives both the permissible labels and their meanings. Performance should then be measured against an evaluation set before additional prompt complexity is introduced. Few-shot examples are also sound for extraction because examples containing the exact field names demonstrate the required schema and reduce formatting ambiguity. Anthropic identifies examples as one of the most reliable methods for steering output format, structure, and consistency. Prompting Best Practices

Chain-of-thought is not an unconditional default. Additional reasoning is appropriate when the task requires substantive decomposition or complex judgment, but routine classification and extraction may gain little while consuming more tokens and increasing latency. The technique should be selected according to evaluated task requirements.

An even-handed comparison governed by explicit criteria mitigates leading-question bias by requiring symmetrical treatment of alternatives rather than presupposing a preferred conclusion. Finally, prompt validation is model-specific. New model versions may follow instructions differently, change formatting behavior, alter tool selection, or produce different latency and cost characteristics. Anthropic’s migration guidance consequently recommends reevaluating prompts and workloads against the new baseline. Model Migration Guide

Study Guide references/topics: Zero-shot prompting; few-shot examples; reasoning techniques; neutral framing; model migration and regression evaluation.

===============

Lifecycle continuity depends on preserving validated knowledge and feeding operational learning back into subsequent phases. Carrying the evaluation framework and reference set forward, as stated in Option B, creates a stable baseline across prompt changes, model migrations, retrieval adjustments, and architectural revisions. Rebuilding the evaluation system each time would undermine longitudinal comparison because changes in the test framework could be mistaken for changes in solution performance.

Option D establishes the second essential continuity mechanism: lessons from discovery, design, implementation, deployment, and production monitoring become explicit inputs to the next phase. This closes the feedback loop and prevents recurring defects, invalid assumptions, and operational findings from being lost at organizational handoffs.

Option A is overly mechanical. Stakeholders should receive communications relevant to their responsibilities and decision rights, not indiscriminate notifications at every transition. Option C confuses comprehensive archival with lifecycle continuity; retention must follow business, regulatory, security, and records-management requirements rather than an unconditional “archive everything” policy. Option E is directly contrary to iterative architecture. Decisions should be documented and governed, but material evidence or changed requirements must be allowed to reopen them.

Study Guide references/topics: Lifecycle phases; evaluation continuity; reference datasets; feedback loops; lessons learned; decision records; iterative architecture governance.

===============

A complete handoff package must help different stakeholders understand, operate, troubleshoot, and evolve the Claude-based solution. An architecture overview explains the system’s structure and responsibilities, while Architecture Decision Records document important decisions, alternatives, and trade-offs. Component-level diagrams provide implementation context without forcing maintainers to reconstruct dependencies from source code. Operational runbooks and an on-call playbook enable reliable incident detection, diagnosis, escalation, and recovery. Documenting known limitations is particularly important for Claude applications because model behavior can vary with prompts, context, input distribution, and external dependencies. Options B, C, and D each provide only a partial or temporary understanding of the system. They would create knowledge gaps, increase operational risk, and make future maintenance dependent on individuals rather than durable organizational documentation.

================

Claude Code permission decisions can be affected by multiple configuration scopes. The appropriate diagnostic action is to inspect the effective rules and identify the exact deny pattern. Managed policy has the highest precedence, and a deny rule from any applicable scope cannot be overridden by an allow rule elsewhere. The architect must then determine whether the denial represents an intentional security boundary or an incorrectly scoped rule. If correction is justified, only the specific rule should be amended. Repeated retries cannot change a deterministic permission decision. Disabling permissions or granting unrestricted Bash access removes safeguards far beyond the reported problem and violates least privilege. Anthropic’s permission documentation explicitly describes scope precedence and deny-first evaluation. Claude Code permissions

Option C describes indirect prompt injection combined with an outbound transmission channel. The attacker embeds instructions in content that the assistant treats as evidence. If the model follows those instructions, it can retrieve sensitive information and transmit it through the HTTP tool to an attacker-controlled destination. Authorization to read a document does not automatically authorize external disclosure. The architecture should treat retrieved content as untrusted, restrict outbound domains, separate data access from external communication, apply least-privilege tool permissions, and require approval for sensitive transmissions. Options A, B, and D describe normal authorized behavior without evidence of unintended disclosure. Anthropic specifically warns that combining untrusted content, sensitive data, and network tools creates exfiltration risk. Web-fetch security guidance; handling untrusted tool results

Package 1 is designed for security and compliance review because its threat model identifies relevant threats and attack paths, its residual-risk register documents the risks remaining after controls, and its control-mapping table connects safeguards to organizational or regulatory requirements. Package 2 is designed for the product manager because delivered capabilities and roadmap dependencies directly support prioritization, release planning, sequencing, and lifecycle ownership. An engineering implementation team would ordinarily need component diagrams, interface contracts, configuration schemas, deployment instructions, and operational runbooks rather than primarily risk-governance artifacts. An executive sponsor generally needs a concise outcome, cost, risk, and decision summary instead of feature-level dependency details. Effective architecture communication must therefore adapt the content and level of detail to each audience’s responsibilities and decision rights.

An actionable runbook must connect detection, diagnosis, containment, recovery, and escalation. Option B supplies that complete operational chain: alerts identify abnormal conditions; triage procedures guide initial investigation; dashboards and logs provide evidence; escalation paths assign authority; and rollback procedures restore a known-safe state. The runbook should cover model errors, latency degradation, rate limits, tool failures, prompt regressions, cost anomalies, data-governance events, and dependency outages. Anthropic’s operational materials demonstrate incident workflows in which alerts lead responders to logs and runbooks before corrective action. Options A, C, and D each omit information required for an on-call engineer to progress from notification to controlled resolution. Procedures should be tested through exercises and updated after incidents.

Study Guide references/topics: Claude operational and observability patterns; incident response; triage; escalation; rollback; operational readiness.

Per-user, scope-restricted OAuth tokens directly eliminate the shared-credential weakness. Each token represents a distinct user or delegated identity, carries only the permissions required for that user’s role, and can be revoked independently. This supports least privilege, limits the blast radius of credential compromise, and enables authorization decisions to be tied to a specific principal instead of an undifferentiated shared API key.

Actor attribution in tool-call logs directly resolves the second finding. Each audit event should record the authenticated user, delegated service identity, session or request identifier, tool name, authorization decision, relevant resource, timestamp, and outcome. This establishes accountability and permits incident investigators to reconstruct who initiated a consequential action.

Moving credentials into a server-side secret store is sound secret-management practice, but it does not by itself correct the shared-identity problem: a centrally stored key can still represent every user as the same principal. Schema validation protects downstream processing, while retrieval-layer RBAC protects information access; neither addresses the two specific audit findings.

These controls should be reinforced by short-lived tokens, server-side authorization enforcement, sensitive-field redaction, and tamper-resistant audit-log retention.

Study Guide references/topics: [Claude Code security](https://docs.anthropic.com/en/docs/claude-code/security); [MCP authentication and OAuth] (https://docs.anthropic.com/en/docs/claude-code/mcp); least privilege; identity propagation; auditable tool execution.

===============

The evaluation metrics must map directly to the two stated requirements. Role-based access-control enforcement rate, tested against a red-team dataset, measures whether requests from unauthorized identities, roles, or access paths are consistently denied. It converts the privacy and authorization requirement into an observable security metric and exposes bypass conditions that ordinary functional tests may miss. Because the requirement says patient data must never reach unauthorized roles, the acceptance threshold should be effectively 100% enforcement across representative and adversarial cases.

Per-query token cost directly measures compliance with the financial constraint. The metric should include uncached input, cache reads and writes where applicable, output tokens, thinking tokens, and any other billable components attributed to the request. Results can then be compared with the defined ceiling across normal, boundary, and worst-case inputs.

Anthropic’s evaluation guidance identifies privacy preservation and price as distinct success criteria and emphasizes that criteria must be specific, measurable, and relevant to the application. Define Success Criteria and Build Evaluations

BLEU may assess textual similarity but does not test authorization or cost. Throughput and percentile latency are valuable operational metrics, yet neither directly answers the two requirements in the scenario.

Study Guide references/topics: Multidimensional evaluation; privacy preservation; authorization testing; red-team datasets; token-cost measurement; requirement-to-metric traceability.

===============

Model identity and version are essential diagnostic dimensions. Without them, operators cannot correlate a behavioral change with a model migration, reproduce the conditions of a failed turn, compare performance among model versions, or distinguish model drift from prompt, retrieval, and application defects. Therefore, the omission described in Option D is a genuine observability gap.

Option E is equally significant. A multi-agent execution normally crosses orchestration, model, agent, MCP, and tool boundaries. If the request-scoped correlation identifier or distributed trace context is lost at any boundary, the resulting spans cannot reliably be reconstructed into one end-to-end transaction. Anthropic’s monitoring guidance explains that distributed tracing links a user prompt to the API requests and tool executions it initiates; it also documents propagation of W3C trace context to supported subprocesses and outbound MCP requests. Claude Code Monitoring

Options A and B describe healthy telemetry coverage rather than gaps. Option C is also appropriate because recording tool interactions supports investigation, while redaction reduces the risk of exposing sensitive data in logs.

Study Guide references/topics: Integration—observability challenges at scale; distributed tracing; correlation identifiers; model-version attribution; privacy-aware tool telemetry.

===============

The evaluation specification must exist before inference begins. Option D defines what the evaluation will measure and how results will be segmented. Representative cases measure normal workload performance, edge cases test boundary behavior, and adversarial cases examine safety, security, or robustness under hostile inputs.

Option B then supplies the correctly curated and labeled dataset corresponding to those slices. Labels, expected outcomes, grading rubrics, provenance, and dataset versions must be established before the deployment generates outputs. Otherwise, evaluators risk modifying criteria after seeing results and introducing confirmation bias.

Anthropic defines an evaluation as an input combined with grading logic used to measure success. Its evaluation guidance distinguishes tasks, trials, graders, traces, outcomes, and the harness that runs and aggregates them. Demystifying Evals for AI Agents

Option E occurs after model execution because outputs must exist before they can be scored. Option A follows scoring and aggregation. Option C is an iterative improvement step performed after failure cases become available, although rubric calibration may also be conducted on separate development data.

Study Guide references/topics: Evaluation specification; metrics and slices; representative and adversarial datasets; labeling; scoring; aggregation; release gates.

===============

Sound human-in-the-loop design places review before a high-impact or irreversible action occurs. The reviewer must receive sufficient context and explicit approval criteria so that the checkpoint functions as a meaningful control rather than a ceremonial step. This is especially important when Claude outputs could initiate financial transactions, publish sensitive material, alter access rights, affect employment decisions, or trigger other consequential actions. Option A provides only retrospective auditing and cannot prevent harm. Option C may support monitoring or quality measurement, but random sampling does not protect every case that requires mandatory approval, particularly when review criteria are undefined. Option D removes the accountability and intervention mechanism entirely. Therefore, B provides the strongest design by combining risk-based placement, human authority, and clearly defined verification requirements before execution.

Option A combines the contractual, technical, and operational measures relevant to a defensible GDPR posture. For commercial services, the Data Processing Addendum defines processor obligations and incorporates safeguards such as Standard Contractual Clauses where applicable. Anthropic states that its DPA is incorporated into its Commercial Terms, while the customer remains responsible for determining lawful purposes, issuing processing instructions, and fulfilling controller obligations.

A defined retention configuration ensures personal data is not retained indefinitely without a documented purpose. Redacting personal information that is unnecessary for the task implements data minimization and reduces exposure in prompts, logs, retrieval stores, and model outputs. Documented data-subject-rights procedures support access, correction, deletion, restriction, and other applicable requests by ensuring the organization can locate and act on relevant records.

Enterprise deployment alone does not establish compliance; the organization must configure and govern the service consistently with its processing activities, risk assessment, lawful basis, and contractual commitments. Options B, C, and D intentionally remove those controls or promote excessive collection.

Study Guide references/topics: [Anthropic Data Processing Addendum guidance](https://privacy.anthropic.com/en/articles/7996862-how-do-i-view-and-sign-your-data-processing-addendum-dpa); [commercial data-retention practices] (https://privacy.anthropic.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data); GDPR data minimization; retention governance; data-subject-rights procedures.

===============