Anthropic introduced the Claude Certified Architect certification, and the Foundations exam is less about trivia and more about judgment: given a realistic agent-engineering situation, what is the right call? I could not find a good free way to practice that, so my team at CyberSkill built one, and this post breaks down what the exam tests and how we think about each area.
The mock is free and needs no login: https://ccaf.cyberskill.world
The shape of the exam
The Foundations exam is 60 scenario questions in 120 minutes, scored out of 1000, with 720 to pass. Our mock mirrors that: a timer, a score, and an explanation of every option. The questions are split evenly across four areas.
1. Research pipelines
Multi-agent orchestration, recovering state after a failure, and handing context between a coordinator and its sub-agents without bloating the window. The recurring lesson: persist compact, structured results per agent and resume only the unfinished work, rather than replaying full histories or starting over.
Five sample questions on research pipelines, with answers: https://ccaf.cyberskill.world/sample-questions/research_pipeline
2. Extraction pipelines
Tool contract design and reliable structured output when inputs are ambiguous. The dependable pattern is to make extraction a contract: a strict schema or tool that the model must satisfy, plus validation and a retry, instead of hoping a prompt returns clean JSON.
Five sample questions on extraction pipelines, with answers: https://ccaf.cyberskill.world/sample-questions/extraction_pipeline
3. Customer support agents
Graceful degradation and honest failure handling. When a tool is down, the right behavior is to say so plainly, give a realistic next step, and offer to escalate, not to guess a status or give a false assurance.
Five sample questions on customer support agents, with answers: https://ccaf.cyberskill.world/sample-questions/customer_support
4. Code exploration
Working in large codebases and scoping an agent's search. The context-efficient move is to search for the known identifier first and open only the files that match, rather than reading everything into context.
Five sample questions on code exploration, with answers: https://ccaf.cyberskill.world/sample-questions/code_exploration
Try it
There are sample questions with answers for each area, four on the index and five more per domain, if you want a taste before the full sitting: https://ccaf.cyberskill.world/sample-questions
The full mock is at https://ccaf.cyberskill.world. It is unofficial and not affiliated with Anthropic. If you take it, I would value your read on whether the questions match the real exam's difficulty.
