Claude Certified Associate – Foundations Exam

The exam is written against seven content domains, and the weights are not even. Output Evaluation and Validation is the largest at 21% — more than double the smallest, Troubleshooting and Optimization at 10% — which tells you what Anthropic considers the core professional skill: not getting an answer out of Claude, but knowing whether to trust it.

• Output Evaluation and Validation — 21%
• Workflow Integration and Solution Design — 16%
• Governance, Risk, and Responsible Use — 15%
• Prompting and Task Execution — 14%
• Product and Model Selection — 12%
• Configuration and Knowledge Management — 12%
• Troubleshooting and Optimization — 10%

Anthropic describes each percentage as the approximate proportion of scored items drawn from that domain, set by a job task analysis of what competent performance requires — which makes the weights the right proportions for your study time too.

The exam fee is $99 USD, and the price at checkout reflects any discount that applies to your organization's partner tier. The fee applies to each attempt, so a retake costs the same again.

You can cancel or reschedule up to 24 hours before your appointment; a change inside that window, a no-show, or arriving after the late-arrival window forfeits the fee.

If you do not pass, the wait before retaking grows each time — 14 days after a first failure, 30 after a second and 90 after a third — and you can take the exam at most four times in a rolling twelve months. A credential, once awarded, is valid for 12 months.

The exam has 60 items in 120 minutes. Items are multiple choice and multiple response, and each multiple-response item states how many answers to select — so read the stem for that number before you read the options.

It is delivered by Pearson VUE, either online proctored or at a Pearson test center.

Scoring is criterion-referenced: you are measured against a fixed standard, not against other candidates. The result is pass or fail with a scaled score from 100 to 1,000, and the cut score is 720. Your report also shows the percentage you answered correctly in each domain, but those percentages do not decide the result — only the total scaled score does.