Exam guide: Claude Certified Associate – Foundations
Who the Claude Certified Associate – Foundations exam is for
According to its exam guide, this certification validates that an individual can apply Claude to complete business and productivity tasks with minimal guidance: using built-in platform features, spotting processes Claude can improve, balancing quality, efficiency and cost, and recognizing limitations so that more complex or technical work is escalated to Claude Architects and Developers. It targets people who use Claude as a productivity tool in roles such as operations, marketing, project management, education and communications.
The guide sets no mandatory prerequisite and states that no software-development or API experience is needed; it recommends regular, hands-on use of Claude at work. It also says what the exam is not: it is not aimed at developers who build against APIs or design agentic systems. Access is restricted: Anthropic's "Who can take an exam" page states that Claude certification exams are open to people who work at organisations in the Claude Partner Network, with registration through a company email on a domain listed in the organisation's partner record. Candidates must be 18 or older and hold a government-issued ID.
Exam format
| Parameter | Value |
|---|---|
| Exam code | CCAO-F (exam guide version 1.0, effective July 2026) |
| Number of items | 60 |
| Item format | Multiple choice and multiple response; each item states how many responses to select |
| Time limit | 120 minutes |
| Delivery | Proctored, online and/or at a test center, per program policy |
| Passing score | Scaled score of 720 on a scale of 100 to 1,000 |
| Results | Pass or fail with the scaled score, plus the percentage of correct answers by domain |
| Validity | 12 months from the date the credential is awarded |
The credential is time-limited because, as the guide puts it, the underlying technology evolves rapidly. Renewing on time means reviewing what has changed and completing a free, non-proctored assessment on the Anthropic Partner Academy. If the credential lapses, the full exam must be taken again.
Domains and weights
| Domain | Weight | Main objectives |
|---|---|---|
| Prompting and Task Execution | 14 % | Effective prompts, task decomposition, iterating on prompts, adapting the strategy to analysis, research, drafting or brainstorming |
| Output Evaluation and Validation | 21 % | Accuracy and completeness, hallucinations, inconsistencies and biases, fact-checking, when human review is required, adapting outputs to the audience, choosing the output format |
| Product and Model Selection | 12 % | Projects, research mode, chat and artifacts; Haiku, Sonnet and Opus; cost, speed and quality; context limits and when to restart, summarize or persist |
| Workflow Integration and Solution Design | 16 % | Analyzing requirements, research and planning, supporting solution design, fitting Claude into existing workflows, explaining value and limits to stakeholders |
| Configuration and Knowledge Management | 12 % | Projects with instructions and knowledge sources, uploaded knowledge and connectors such as Google Drive and Gmail, system-level instructions, keeping configurations up to date |
| Governance, Risk, and Responsible Use | 15 % | Appropriate and inappropriate use cases, data sensitivity, regulation and privacy, organisational AI policies, ethical implications |
| Troubleshooting and Optimization | 10 % | Diagnosing underperforming prompts or poor outputs, adjusting from feedback, making workflows more efficient |
The guide gives these weights as approximate. Output evaluation (21 %) and governance (15 %) together account for roughly 36 % of scored items: checking what Claude produces, and deciding which uses and data are appropriate. Prompting itself weighs 14 %.
How to prepare
- Read the exam guide in full and self-assess against each objective of its blueprint.
- Check your eligibility on the "Who can take an exam" page before planning anything else.
- Take the Associate – Foundations prep course. Its page recommends three courses first: Claude 101, AI Fluency: Framework & Foundations, and AI Capabilities and Limitations.
- Read the help articles on the features the guide names: Projects, Artifacts, Memory, Skills and Code Execution.
- Build one real Project for a recurring task: instructions, knowledge files, a connector if your organisation allows it. Run it on several cases and note where the output needs correcting.
- Practise checking outputs: verify each figure and citation against its source, look for omissions and bias, and decide in advance which deliverables need a human review.
- Do the sample questions in section 8 of the guide to get used to the item style.
- Practise with our Claude Certified Associate practice exam under timed conditions, then review each missed question in the free study mode.
Practice Exam: Claude Certified Associate – Foundations
25 free questions with explanations, no account needed.