Your application uses the Messages API to handle multi-turn conversations. Each new turn resends the entire conversation history, and your token costs are growing as conversations get longer. You suspect there is a more efficient approach.
How would you address this?

• A. Use prompt caching to reuse the static portions of the conversation context across turns instead of paying for them at the normal input-token rate on every request the application sends.
• B. Truncate every conversation to the last two messages so that token usage stays low and costs remain predictable across the application's normal operation.
• C. Switch to the Batch API for every turn so the per-call cost is reduced, treating the batch as the team's primary cost-control mechanism for multi-turn work.
• D. Summarize each conversation after every turn and replace the full history with the summary on the next request, reducing token count at the cost of fidelity.

You are building an MCP server that exposes several internal data sources as MCP resources. The server needs to be deployed so multiple Claude applications can integrate with it.
How would you approach the build and deployment?

• A. Deploy the MCP server only on individual developer machines, with the Claude applications unable to reach the server outside each developer's machine.
• B. Bypass the MCP server and embed each data source directly in every Claude application that needs the data, with each application maintaining its own integration.
• C. Author the server with clearly defined resources, tools, and prompts, choose a communication pattern, and deploy to an accessible hosting environment.
• D. Build the MCP server with resource and tool definitions scoped to the first Claude application that needs it, and extend the definitions to additional applications as each integration is requested.

You are writing a system prompt for a Claude application that needs to produce output in a specific JSON shape. The downstream system will reject any output that does not match the schema.
Your prompt would need to...

• A. Instruct Claude to return JSON sometimes and free text other times so the application's output captures both formats.
• B. Include explicit constraints describing the required JSON schema and an instruction to produce only output matching that schema.
• C. Instruct Claude to use whichever output format it considers most appropriate for each request the application handles.
• D. Omit any reference to the format and rely on a post-processing step in the application to reshape Claude's output.

A Claude application that worked well in testing is now occasionally returning outputs that mention information not present in the input. The development team initially assumed the model was hallucinating, so they asked you to troubleshoot.
What would you do first?

• A. Apply a retrieval-augmented generation pattern to ground the responses in source content before any further investigation of the production traces.
• B. Replace the current model with a larger one to reduce the chance of hallucination, on the grounds that larger models tend to hallucinate less in typical applications.
• C. Add a system prompt instruction telling the model not to invent information, on the grounds that prompt-level instructions are the fastest fix for hallucination concerns.
• D. Examine production traces to identify whether the issue is hallucination by the model, context loss, prompt injection, or another failure mode before recommending a fix.