A new Claude model release includes performance improvements for several reasoning tasks but has changed the format of its responses to system prompts that use multi-section instructions. Your application uses multi- section system prompts heavily. Initial evaluation on the application's actual workload shows the new model performs 8 percent better on reasoning tasks but produces malformed output on roughly 3 percent of requests because of the format change. The team is debating whether to upgrade.
How would you decide?

• A. Adapt the application's system prompt to the new model's format expectations and re-evaluate, then upgrade only if the adapted prompt eliminates the malformed output while preserving the reasoning improvements.
• B. Upgrade immediately, because the 8 percent reasoning improvement outweighs the 3 percent malformed output rate across the application's typical request distribution.
• C. Upgrade and add a downstream validation step that catches the 3 percent malformed output before it reaches users, treating the validation step as the team's mitigation for the format change.
• D. Stay on the previous model permanently to avoid the malformed output rate and any future format changes that subsequent model releases might introduce in the application.

Your Claude application is hitting context window limits when processing long customer service transcripts.
A junior developer suggests increasing the temperature parameter to fix the issue.
How would you respond?

• A. Adjust the temperature parameter together with the max_tokens parameter, treating the combined adjustment as the team's mechanism for managing context window pressure during long-transcript processing.
• B. Remove the system prompt entirely to make room for longer transcripts in each request, freeing up context window space the system prompt would otherwise consume.
• C. Increase the temperature parameter as the junior developer suggested and observe whether the context window issue resolves over the next several runs of the application in production.
• D. Explain that temperature controls sampling randomness and is unrelated to context capacity, then address the context issue through summarization or chunking.

Your agent makes 10 to 15 tool calls per task, and you have noticed it sometimes loses track of earlier results by the time it reaches later steps. The agent's context window is large enough to hold all the messages, but the relevant information appears to get buried as the conversation grows.
How would you address this?

• A. Reduce the number of tool calls per task by combining several existing tools into larger, multi-purpose tools.
• B. Apply a context-management pattern that summarizes or prunes older tool outputs while preserving the active task state.
• C. Increase the context window further so all tool outputs from every prior step remain in full detail throughout the task.
• D. Switch to a different agentic framework that advertises automatic context-window management as a built-in feature.

Your Claude application is deployed to development, staging, and production environments. Each environment uses a different model version, different prompt versions, and different plugin dependencies, but the configuration is currently scattered across environment variables, hardcoded values, and undocumented setup scripts.
How would you manage the configuration?

• A. Use the latest available model version everywhere and stop pinning model versions, on the grounds that pinning adds maintenance overhead the team should aim to reduce.
• B. Standardize all environments to use the same configuration values to eliminate the differences between development, staging, and production.
• C. Move all configuration into hardcoded application code to reduce reliance on external configuration sources that are difficult to track over time.
• D. Consolidate the configuration into a version-controlled system documenting model version pinning, prompt versioning, and plugin dependencies for each environment.