About the Exam

Anthropic's foundation-level certification for software engineers who build and ship applications, agents and workflows on Claude. The 53-item, 120-minute exam weights API and application integration most heavily, then model selection and cost optimization, agent design, prompt and context engineering, custom tools and MCP servers, security, Claude Code and evals. Passing demonstrates the ability to take a Claude integration into production.

Exam Topics

  • Applications and Integration33–34%
  • Model Selection and Optimization16–17%
  • Agents and Workflows14–15%
  • Prompt and Context Engineering11%
  • Tools and MCPs10–11%
  • Security and Safety8–9%
  • Claude Code3–4%
  • Eval, Testing, and Debugging2–3%

How to Use This Practice Exam

  1. Browse — Read each question, select your answer, and reveal the explanation.
  2. Exam Mode — Simulate real exam conditions with a timed session and score report.
  3. Learn Mode — Spaced repetition schedules questions you struggle with for long-term retention.

Download the Full Exam PDF

Get every question and answer in a clean, printable PDF built for offline study. Purchase once, keep permanent access, and re-download the latest version anytime.

Last updated November 3, 2026 at 4:44 PM

Topic filter
Question status
Question sort
Questions per page

QuestionQ1

VerifiedSecurity and Safety

Your Claude application's content policy defines categories of content that it must never produce under any circumstances. The application currently has no way to enforce this policy, and content in these categories is appearing in its output. How would you enforce the content policy?

Explanation

Deterministic output filtering evaluates each generated response against the defined prohibited categories before it is delivered to users, enabling matching content to be blocked consistently. System-prompt instructions may steer model behavior but are not a guaranteed enforcement control.

Community Discussion

No comments yet. Be the first to start the discussion!

QuestionQ2

VerifiedSecurity and Safety

Your Claude application’s API keys are kept in a secrets manager. The team is considering whether to use the same key in development, staging, and production. How should the keys be handled across environments?

Explanation

Each environment should use its own API key. Environment-specific credentials isolate compromise, revocation, auditing, permissions, and rotation, so exposure in development or staging does not grant access to production. Anthropic documentation also recommends creating a dedicated API key for direct API use and storing it securely.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!

QuestionQ3

VerifiedTools and MCPs

The team is considering whether to implement a new capability as a custom tool or use an existing built-in tool that almost meets the use case but is missing one specific feature. How should you make the decision?

Explanation

Choose the approach based on whether the built-in tool can be extended to support the missing feature and whether that is preferable to the flexibility, implementation effort, and ongoing maintenance of a custom tool. This evaluates the relevant technical and lifecycle trade-off across both options.

Community Discussion

No comments yet. Be the first to start the discussion!

QuestionQ4

VerifiedTools and MCPs

A teammate has asked for an explanation of when a Skill is the better choice than an MCP server. The teammate is unsure how the two differ in practice when both can be reused across teams. How would you describe the distinction?

Explanation

A Skill packages instructions and optional workflow resources, including scripts, templates, and references, to guide repeatable work. An MCP server exposes live information and controlled actions through a standard client-server interface, including tools, resources, and prompts. Skills can complement MCP servers by defining how to use their capabilities for a workflow.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!

QuestionQ5

VerifiedPrompt and Context Engineering

You are creating a system prompt for a Claude application that must generate output in a particular JSON shape. The downstream system will reject any output that fails to conform to the schema. Your prompt would need to ...

Explanation

When a downstream system requires a particular JSON schema, the model must receive explicit instructions defining that schema and requiring output only in that format. Clear, specific output-format constraints improve compliance and prevent extra free text or incompatible structures.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!
Know a question that should be here? Contribute to this exam
Back home