Your Claude application's outputs are inconsistent in format. The team's instructions are scattered across the system prompt and user messages, with some instructions stated only once and others repeated.
How would you fix the inconsistency?

• A. Consolidate behavioral and format instructions in the system prompt and keep user messages focused on the user's input.
• B. Repeat all instructions in both the system prompt and the user message so the model sees each instruction more than once.
• C. Move all instructions into the user message so the application's behavior is controlled at the input point.
• D. Place each instruction wherever the developer who first wrote it found most natural, retaining the original intent.

Your Claude application's API keys are stored in a secrets manager. The team is debating whether the same key should be used in development, staging, and production environments.
How would you handle the keys across environments?

• A. Use distinct keys for each environment so a compromise in one environment does not affect the others during normal operation across the application's lifecycle.
• B. Rotate the same key across environments at random intervals on the grounds that random rotation provides isolation between environments without requiring distinct keys.
• C. Use a single development key everywhere on the grounds that production keys are too risky to deploy across the application's three environments during normal operation.
• D. Use the same key across all environments for simplicity and treat the propagation of any compromise as a known operational tradeoff for the team's key management approach.

You are deciding between Claude models for a task. The team has identified three relevant tradeoff dimensions: quality, latency, and cost.
The right model is the one that...

• A. Meets the task's cost target within a defined latency budget, with quality validated against a representative sample of inputs after the model is selected.
• B. Meets the task's quality requirements at an acceptable latency, with cost reviewed separately once the quality and latency bar has been established.
• C. Satisfies the task's latency requirement first, then is evaluated against quality and cost thresholds to confirm the selection is acceptable across all three dimensions.
• D. Fits the task's quality, latency, and cost requirements together, recognizing that improving one dimension typically affects the others.

Your Claude application has been running for several conversation turns, and you notice the model occasionally references information that was discussed many turns ago but is no longer relevant. You suspect context drift is causing the model to weight stale content too heavily.
How would you address the drift?

• A. Reset the conversation after every turn so the model loses all prior turns when generating a response.
• B. Increase the context window size so all turns of the conversation remain visible to the model in full detail.
• C. Truncate the conversation so the model sees only the most recent turn during each subsequent response.
• D. Apply compaction to summarize older portions of the conversation so the gist remains while the specifics carry less weight.

You are explaining to a stakeholder why running the same Claude prompt twice can produce slightly different results. The stakeholder is concerned this means the application is broken.
How would you address the stakeholder's concern?

• A. Tell the stakeholder the variation is a bug that the team will fix in the next release of the application, then create a work ticket to fix the bug.
• B. Explain that LLMs are non-deterministic by default due to sampling, and describe how the application handles this through validation, retries, or temperature adjustment.
• C. Tell the stakeholder the variation is caused by Claude being updated continuously by Anthropic, and that switching to a fixed model snapshot will eliminate the variation entirely.
• D. Tell the stakeholder the variation comes from network latency and that switching to a faster network connection will produce more consistent results across runs.