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.

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

Option B is the intended and technically correct answer. The supplied Claude Developer exam source selects streaming responses. Streaming allows the client application to begin receiving output before generation of the complete message has finished, reducing perceived latency for interactive user experiences.

Anthropic's official Messages API documentation states that setting stream: true causes responses to be delivered incrementally through Server-Sent Events (SSE) . Claude can stream text deltas as well as other event types, including structured tool-use and extended-thinking events where applicable. Anthropic's SDKs provide corresponding synchronous or asynchronous streaming helpers.

The application consumes events as they arrive, updates the UI progressively, and then handles the final event or stop reason when generation completes. This architecture is particularly useful for chat interfaces and other latency-sensitive interactive experiences.

A addresses output structure, not progressive transmission. C is designed for asynchronous, throughput-oriented processing rather than immediate user interaction. D reduces processing cost and latency for repeated prompt prefixes but does not itself turn a response into an incremental stream.

Relevant Claude Developer topics: Messages API, streaming, SSE, incremental tokens, latency, event handling, interactive applications, and API response mechanics .

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

Option A correctly treats this as a context-dependent format drift problem rather than an arbitrary model failure. Because the application initially produces valid JSON and progressively loses structure over subsequent turns, the investigation should focus on how accumulated conversation history changes the instructions and examples visible to Claude. Earlier malformed outputs, conflicting instructions, tool results, or unnecessary historical content can gradually reduce adherence to the intended format.

The application should therefore inspect the conversation state, preserve the authoritative formatting requirement, prune irrelevant content where appropriate, and validate outputs at the application boundary. Anthropic's Structured Outputs capability is specifically designed to prevent malformed structured responses by constraining Claude to a supplied JSON Schema. Official guidance states that Structured Outputs provide valid, parseable, schema-compliant results for downstream processing.

B destroys the response rather than correcting the failure mode. C resets state but prevents meaningful multi-turn operation and does not diagnose why context causes drift. D changes model characteristics without establishing that the model is responsible.

The supplied question on page 12 identifies A as correct. Relevant topics: Agent Architecture, context engineering, format drift, structured outputs, context evolution, schema validation, and long-running conversations.

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