Anthropic : CCDV-F Questions & Answers

Your team's Claude application has been in production for a year, and the team has decided to formalize its testing strategy. Currently, the team writes ad-hoc tests for individual features but has no overall testing approach.
What testing approach would you formalize?

• A. Adopt a test-driven development practice where unit tests are written before each feature is implemented and must pass before code is merged.
• B. Define unit tests for individual functions, integration tests for the Claude integration, and end-to-end tests for critical user flows, applied consistently across the codebase.
• C. Continue writing ad-hoc tests as features ship and introduce a peer review step to ensure each test adequately covers the feature being released.
• D. Define a single testing approach that uses end-to-end tests and apply it consistently across all new features as they are added to the codebase.

The Anthropic API deprecated a request parameter that your Claude application uses in approximately 40 places across the codebase. The deprecation notice gives a six-month window before the parameter is removed and recommends a replacement parameter with slightly different semantics.
You would respond to the deprecation by...

• A. Keeping the deprecated parameter in place while writing a wrapper function around it to insulate the rest of the codebase from the eventual change.
• B. Adding regression tests to cover the parameter's behavior, then migrating call sites in batches that you validate against regression tests.
• C. Migrating all 40 call sites in a single change near the removal date to ensure the deprecated parameter continues to work as long as possible.
• D. Swapping all 40 call sites in a single change right away to prevent drawn-out migration work that will delay ongoing functioning.

You are running Claude Code as part of an automated continuous integration pipeline. The pipeline needs Claude Code to execute a set of well-defined tasks without prompting for confirmation, and the output needs to be captured for downstream processing.
How would you configure the pipeline?

• A. Replace Claude Code with a different tool that does not require any configuration to operate without confirmation prompts in the pipeline.
• B. Run Claude Code in interactive mode and have a developer manually approve every confirmation prompt while the pipeline executes its tasks.
• C. Run Claude Code in headless mode with the required permissions configured in settings.json and capture its output for downstream processing.
• D. Disable Claude Code's confirmation prompts globally across all environments so the pipeline runs without interruption from any prompt.

Your team is debating how to manage the prompts used in your Claude application. Some prompts are checked into the code repository, some live in a separate configuration file, and some are constructed inline at runtime. The result is inconsistent, and a recent prompt change went out without code review.
What steps would you take?

• A. Establish a single source of truth for prompts, version-control them alongside code, and require code review for prompt changes.
• B. Establish a single source of truth for prompts but keep change review optional, allowing developers to update prompts directly when changes are urgent.
• C. Move all prompts out of version control to a separate spreadsheet that team members can edit freely as the application evolves over time.
• D. Move all prompts to inline runtime construction so the team can update them quickly through a streamlined process outside the standard code review workflow.

Your Claude agent's hooks are currently triggered for every action, which slows down the agent significantly even when actions pose no risk. The team wants to scope hooks more carefully.
How would you scope the hooks?

• A. Replace hooks with system prompt instructions on the grounds that prompt instructions can produce the same enforcement effect that hooks produce on the agent's actions.
• B. Scope hooks to only the high-risk actions, such as destructive operations or sensitive data access, and remove hooks from low-risk actions to balance safety with performance.
• C. Disable all hooks while the team re-scopes them, treating the period of no hook enforcement as a temporary state during the re-scoping work.
• D. Disable the agent during peak hours so the hook overhead does not slow the application down during the busiest periods of the day across the application's operation.