Practice Questions

Production data shows that in 12% of cases your agent skips get_customer entirely and calls lookup_order using only the customer's stated name, occasionally leading to misidentified accounts and incorrect refunds. What change would most effectively address this reliability issue?

Logs show the agent frequently calls get_customer when users ask about orders (e.g., "check my order #12345") instead of lookup_order. Both tools have minimal descriptions and accept similar identifier formats. What's the most effective first step to improve tool selection reliability?

Your agent achieves 55% first-contact resolution, well below the 80% target. It escalates straightforward cases (standard damage replacements with photo evidence) while attempting complex situations requiring policy exceptions. What's the most effective way to improve escalation calibration?

You want a custom /review slash command that runs your team's standard code review checklist, available to every developer when they clone or pull the repository. Where should you create this command file?

You must restructure the team's monolithic application into microservices - changes across dozens of files, with decisions about service boundaries and module dependencies. Which approach should you take?

Your codebase has distinct areas with different conventions. Test files are spread throughout alongside the code they test (e.g., Button.test.tsx next to Button.tsx), and you want all tests to follow the same conventions regardless of location. What's the most maintainable way to ensure Claude automatically applies the correct conventions?

Researching "impact of AI on creative industries," each subagent completes successfully, but the final reports cover only visual arts, missing music, writing, and film. The coordinator's logs show it decomposed the topic into "AI in digital art creation," "AI in graphic design," and "AI in photography." What is the most likely root cause?

The web search subagent times out while researching a complex topic. You need to design how this failure flows back to the coordinator. Which error propagation approach best enables intelligent recovery?

The synthesis agent frequently needs to verify claims. Currently it returns control to the coordinator, which invokes the web search agent and re-invokes synthesis - adding 2-3 round trips and 40% latency. 85% of verifications are simple fact-checks; 15% require deeper investigation. What's the most effective approach?

Your pipeline runs claude "Analyze this pull request for security issues" but the job hangs indefinitely, waiting for interactive input. What's the correct approach to run Claude Code in an automated pipeline?

Two workflows use real-time Claude calls: (1) a blocking pre-merge check that must complete before developers merge, and (2) a technical debt report generated overnight. Your manager proposes switching both to the Message Batches API for its 50% cost savings. How should you evaluate this?

A PR modifies 14 files. Your single-pass review produces inconsistent results: detailed feedback for some files, superficial for others, obvious bugs missed, and contradictory feedback (flagging a pattern in one file while approving identical code elsewhere). How should you restructure the review?