A teammate has asked you to explain why the team's Claude application is billed for output tokens at a different rate than input tokens. They had assumed the rate was the same for both.
How would you explain the difference?

• A. Output tokens are not billed at all, because cost is determined entirely by the input tokens sent to the model on each request.
• B. Output tokens are typically billed at a lower rate than input tokens, because output tokens are cheaper to produce than input tokens are to process.
• C. Output tokens are typically billed at a higher rate than input tokens, and cost models for the application should reflect both rates separately.
• D. Output tokens are typically billed at the same rate as input tokens, and the apparent rate difference is a billing error to report to Anthropic.

You are setting up a Claude application that requires API keys for several external services.
What is the best way to store the keys?

• A. Use a single shared key across all external services, so any developer working on the application can find the keys easily during development.
• B. Store the keys in a secrets manager or environment-specific configuration that is not checked into source code, and load them at runtime.
• C. Put the keys in the application's configuration file and check the configuration file into the team's repository alongside the rest of the source code.
• D. Email the keys to each developer as needed and have each developer paste the keys into their local environment when they begin working on the application's code.

A teammate has asked you to explain the difference between context engineering and prompt engineering.
They have heard the terms used interchangeably and are unsure how each applies to a Claude application that processes long-running multi-step tasks.
How would you describe the distinction?

• A. Prompt engineering is the older term for prompt design, while context engineering is the newer term that has replaced it in modern Claude applications across the industry.
• B. Prompt engineering focuses on the model's response, while context engineering focuses on the user's input across many sessions in a long-running multi-step Claude application.
• C. Prompt engineering shapes individual prompts for specific outputs, while context engineering manages how content flows across turns and steps and takes steps to keep relevant state visible.
• D. Prompt engineering and context engineering each address content the team gives Claude, but the team can group them under a single workflow because the practices use overlapping techniques.

You are designing an agent that handles a complex claim-processing workflow. Each claim moves through fact extraction, eligibility evaluation, and a decision step. The three subtasks have distinct success criteria, and some claims require iteration between fact extraction and eligibility evaluation before a decision can be reached.
Which agent pattern would you apply?

• A. A graph-based pattern that lets the agent move between subtasks based on the state of each claim, with each subtask evaluated against its own criteria.
• B. A single tool-use loop pattern that gives one agent access to all the tools needed for fact extraction, eligibility evaluation, and decision-making.
• C. A streaming pattern that emits partial decisions as the agent processes each claim, refining the output until a final decision emerges from the stream.
• D. A linear chain pattern that processes every claim through fact extraction, then eligibility evaluation, then decision, with no return paths between subtasks.