Option A is the appropriate trust-boundary treatment for external content. Untrusted text can contain malformed data, adversarial instructions, prompt-injection attempts, or content deliberately constructed to alter the agent's behavior. It should therefore be validated or screened before inclusion and clearly represented as untrusted data rather than authoritative application instructions.

Anthropic's prompt-injection guidance distinguishes direct attacks from indirect prompt injection, where Claude processes third-party content such as webpages, emails, documents, or tool output containing hostile instructions. Anthropic recommends input validation and screening, least-privilege access, safe treatment of untrusted tool content, and screening content before Claude acts on it. Importantly, Anthropic notes that tool-result content is treated as untrusted data rather than as a reliable place for application instructions.

B erases the trust distinction and exposes the application to instruction/data confusion. C introduces a deliberately weaker security boundary and does not sanitize the data. D prevents legitimate use cases unnecessarily; untrusted does not mean unusable—it means the data must be handled defensively.

Therefore, A correctly combines validation with explicit trust separation. Relevant Study Guide topics: prompt injection, untrusted content, input validation, sanitization, data/instruction separation, least privilege, and defense in depth.

Option B is correct. A large prompt containing overlapping, contradictory, or obsolete instructions creates instruction ambiguity and increases the likelihood that Claude will apply an unintended rule, over-weight irrelevant guidance, or produce inconsistent behavior.

Anthropic's current prompting guidance reinforces this principle: Claude performs best when instructions are clear, explicit, and direct. Prompt design should minimize ambiguity and provide the model with precisely the context and behavioral requirements needed for the task. Refactoring should therefore remove obsolete requirements, consolidate duplicated instructions, resolve contradictions, and establish one authoritative formulation for each behavioral rule. The revised prompt should then be regression-tested against representative inputs.

A makes an already overloaded prompt larger and relies on instruction ordering instead of eliminating conflicts. C addresses only one defect while retaining redundant and obsolete material. D does not inherently solve contradictions and may fragment authoritative instructions across multiple locations.

Therefore, B addresses the root cause. Relevant Study Guide topics: system prompt design, prompt maintainability, instruction clarity, conflicting instructions, prompt refactoring, regression evaluation, and context quality.

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

Option B is the appropriate software-engineering communication pattern when the application requires a persistent, low-latency, bidirectional channel. WebSockets establish a connection using an HTTP Upgrade handshake and then maintain a TCP-based communication channel in which either side can send messages independently. This eliminates the repeated connection setup and request overhead associated with conventional polling.

RFC 6455 defines WebSocket specifically as a protocol enabling two-way communication and explains that it provides a single TCP connection as an alternative to HTTP polling for interactive communication.

Option A can work for infrequent updates, but repeatedly opening HTTP requests adds latency, headers, and server/client overhead and is unsuitable when continuous real-time communication is the stated requirement. C resembles long polling or an ad-hoc streaming connection but lacks the standardized framing, lifecycle behavior, and interoperability provided by WebSocket. D introduces filesystem polling and is not an appropriate network-streaming architecture.

The important certification principle is selecting a communication mechanism based on application requirements rather than merely choosing an available protocol. For persistent two-way streaming, WebSocket provides the intended abstraction. Relevant Claude Developer topics are software engineering foundations, client-server communication, persistent connections, HTTP versus WebSocket patterns, streaming, and real-time application architecture.

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

Option C follows the governing constraint in the scenario: data residency is an enterprise requirement, whereas minimizing infrastructure management is a preference. A deployment architecture cannot knowingly violate a mandatory compliance boundary merely to accelerate delivery. The question should therefore be interpreted under its stated assumption that the described BYOC environment satisfies the enterprise residency policy.

Anthropic's current Managed Agents documentation distinguishes Anthropic-managed cloud environments from self-hosted sandboxes running on infrastructure controlled by the customer. Self-hosting keeps tool execution, files, and network egress within customer infrastructure, although Anthropic documents that model-facing tool inputs and outputs can still pass through its control plane; therefore, actual regulatory approval must be based on the organization's precise data-flow requirements.

B and D explicitly defer or violate the existing policy. A unnecessarily introduces a planned migration away from the residency-compliant architecture without establishing that such a migration would be permissible.

Accordingly, C is the intended certification answer. Relevant Study Guide topics: deployment topology, data residency, self-hosting, compliance constraints, infrastructure ownership, security boundaries, and architecture tradeoffs.

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

Option C matches Anthropic's efficiency-first model-selection guidance. For a straightforward, high-volume workload where latency and unit cost are explicit constraints, the correct starting point is a faster, economical model that can meet the task's quality threshold. Anthropic specifically lists high-volume straightforward tasks, tight latency requirements, and cost-sensitive implementations as cases where an efficiency-first model choice is appropriate.

The crucial qualification is that “smaller” does not mean accepting inadequate quality. The team should evaluate the candidate against representative classification examples and defined accuracy criteria. If it passes, moving to a larger model adds cost and often latency without delivering required business value.

A selects a mid-tier model by convention rather than workload evidence. B multiplies inference calls, generally increasing both latency and cost for a simple classification problem. D optimizes maximum capability even though the task does not require frontier-level reasoning.

Therefore, C is the appropriate initial model choice, followed by workload-specific validation. Relevant Study Guide topics: Claude model selection, efficiency-first design, classification workloads, throughput, latency, per-request economics, evaluation, and quality/cost tradeoffs.

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

D applies configuration as code and is the answer explicitly selected in the supplied examination source. Claude Code treats project configuration as part of the repository's working context. Anthropic documents project-level CLAUDE.md as the mechanism for providing project instructions and context, while shared project configuration belongs in .claude/settings.json. Crucially, Anthropic states that .claude/settings.json is intended to be checked into source control and shared with the team .

Keeping these files alongside the code establishes a single versioned relationship between application behavior and the configuration that influences Claude Code. Standard pull requests then provide diffs, peer review, ownership controls, CI validation, audit history, and straightforward rollback. A particular commit can therefore reproduce both source code and its associated Claude project configuration.

A creates competing copies and synchronization risk. B artificially separates behavior configuration from the code version it affects. C creates the same problem specifically for settings.json.

Developer-local values remain distinct: .claude/settings.local.json exists specifically for settings that should not be committed.

Relevant Claude Developer topics: Confia Management, CLAUDE.md, settings.json, configuration as code, source control, pull-request review, reproducibility, auditability, and team-shared Claude Code configuration .

Option A follows disciplined production debugging: diagnose the actual failure mode before changing architecture or prompts. An output containing unsupported information might indeed be hallucination, but similar symptoms can result from stale conversation state, incorrect retrieval, unexpected tool output, prompt injection, incorrect request construction, or mismatched model/configuration versions.

A production trace should capture the user input, system instructions, relevant conversation history, retrieved content, tool calls and results, model/version, request parameters, response, and identifiers necessary to compare successful and failing cases. This establishes whether the model invented a fact or whether that fact entered context through another path.

B changes the model before establishing causality. C may eventually be useful if the confirmed problem is insufficient grounding, but implementing RAG before diagnosis can hide rather than explain the defect. D similarly changes prompting before verifying that prompt behavior is responsible.

The engineering sequence should be observe, reproduce, classify the failure, form a hypothesis, apply a targeted correction, and validate the correction with evaluations. Relevant Study Guide topics: production troubleshooting, observability, tracing, hallucination analysis, prompt injection, context failures, regression diagnosis, and lifecycle monitoring.

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

Option B establishes the correct trust boundary. Fluent or confident language is not evidence that a generated claim is factually correct. If downstream systems treat output as authoritative data, the application must independently establish whether the output meets its correctness requirements before accepting it.

Validation can take several forms depending on the workload: compare generated facts against authoritative records, require citations or source references, constrain output to retrieved evidence, apply deterministic business rules, or use separate evaluation/classification stages. Anthropic's agent engineering guidance repeatedly emphasizes explicit evaluation criteria and validation rather than relying on apparent confidence.

A confuses sampling behavior with factual reliability. Lowering temperature does not establish factual correctness and may only make an incorrect answer more repeatable. C supplies maximum oversight but is unnecessarily expensive and removes useful automation even for low-risk, easily validated cases. D communicates uncertainty to users but does not protect downstream systems that automatically consume the response.

Therefore, B treats model output as untrusted until verified to the level required by the application. Relevant Study Guide topics: output validation, grounding, factuality, confidence calibration, source verification, trust boundaries, and downstream safety.

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