An organization wants predictable outputs for automated invoice classification. Which API parameter should generally be LOWER?

• A. Temperature
• B. Prompt length
• C. Max tokens
• D. Context window

Production logs show that when the agent handles complex billing disputes requiring 6+ tool calls, it sometimes exhausts its max_turns limit after gathering data but before completing resolution or escalating. The team's goal is to guarantee that every customer interaction ends with either a completed resolution or a human handoff, regardless of how the agent loop terminates. Which approach achieves this guarantee?

• A. Split the workflow into two sequential agent invocations - a first agent gathers information via get_customer and lookup_order, then a second agent receives that data and handles process_refund or escalate_to_human, each with separate turn budgets.
• B. Implement a pre-tool-use hook that counts tool invocations and terminates the loop with an automatic escalation once the agent reaches 80% of its max_turns limit.
• C. Add orchestration-layer code that checks the agent's outcome after each loop termination - if the loop ended without a completed resolution or escalation, programmatically call escalate_to_human with the accumulated conversation context and tool results.
• D. Add system prompt instructions telling the agent to call escalate_to_human with a summary of its findings whenever it determines it cannot complete resolution within its remaining actions.

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.
Your pipeline reviews every pull request using a single API call with a static prompt containing the diff and the full text of each changed file. Unchanged files are not included. Developers report that reviews consistently miss cross-file bugs--for example, a pull request renames a function's parameters, but the review does not identify callers in unchanged files that still use the old argument order.
Evaluation shows that cross-file bugs account for 35% of production incidents originating from reviewed pull requests.
What is the most effective change to the review design?

• A. Redesign the review as a turn-limited agentic task that can read files and search the repository, following references to verify cross-file findings.
• B. Add instructions asking the model to list external references and reason step by step about how each change could affect unseen callers.
• C. Build a static dependency graph and include every file located within two dependency hops of a changed file.
• D. Run separate review passes for each changed file with its direct dependants, and then aggregate and deduplicate the findings through a final consolidation pass.

Claude produces occasional factual inaccuracies despite clear prompts. Which architectural enhancement is MOST effective?

• A. Increase temperature.
• B. Shorten responses only.
• C. Add grounding through trusted retrieval.
• D. Remove examples.

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.
Your pipeline includes a release-notes generation step that classifies and summarizes approximately 200 commits at the end of each weekly release cycle. Each commit is currently sent as a separate Messages API request using a Sonnet-tier Claude model. The release notes are not needed until the following morning, providing approximately 12 hours of acceptable latency.
Your team must reduce the per-token API cost while retaining the same model, prompts, and output quality.
Which approach satisfies all these constraints?

• A. Concatenate all 200 commit messages into one Messages API request because reducing the number of requests always reduces token costs.
• B. Submit the 200 requests through the Message Batches API with unique custom_id values and retrieve the results after the batch finishes.
• C. Issue the 200 Messages API requests concurrently because parallel execution reduces the per- token price.
• D. Replace the Sonnet-tier model with a Haiku-tier model to obtain a lower per-token price.