Anthropic CCDV-F Exam Syllabus Topics:

Anthropic Claude Certified Developer-Foundations Sample Questions:

Question 1

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. 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.
C. Truncate every conversation to the last two messages so that token usage stays low and costs remain predictable across the application's normal operation.
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.

Question 2

A Claude application is occasionally refusing to answer questions that should be in scope, including questions the application has answered correctly in the past. You want to investigate.
What is the first step of your investigation?

A. Test whether removing or adjusting those instructions resolves the behavior.
B. Assess whether the refusals cluster around specific input patterns, question types, or time periods by analyzing the distribution of refused requests in the logs.
C. Examine traces of the refused requests to identify what triggers the refusal, whether input patterns, system prompt content, or other context.
D. Identify which questions have been refused and compare them against previously answered questions to determine what changed between the successful and refused interactions.

Question 3

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. 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.
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. Use a single shared key across all external services, so any developer working on the application can find the keys easily during development.
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.

Question 4

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

Question 5

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

Solutions: