Launch Deal · 50% off 1st month ·
← CCAO-F study guide

CCAO-F exam topics

The CCAO-F exam (Claude Certified Associate (Foundations)) covers 7 domains and 30 topics. This page lists all of them with the weight of each domain, so you can see what the exam tests and where most of the marks are.

Domains and weights

DomainWeightTopics
Domain 1: Prompting & task execution14%4
Domain 2: Output evaluation & validation21%6
Domain 3: Product & model selection12%4
Domain 4: Workflow integration & solution design16%5
Domain 5: Configuration & knowledge management12%4
Domain 6: Governance, risk & responsible use15%4
Domain 7: Troubleshooting & optimisation10%3

Domain 1: Prompting & task execution · 14%

Domain 2: Output evaluation & validation · 21%

Domain 3: Product & model selection · 12%

Domain 4: Workflow integration & solution design · 16%

  • Analysing Requirements and Use Cases

    Claude structures; the human validates and owns the result. Structure from Mess: Real requirements arrive as complaint threads, meeting notes, survey comments. Claude clusters them into themes, separates what people asked for from what they appear to need, surfaces incompatible demands, and names what nobody mentioned.

  • Using Claude for Research, Planning and Process Optimisation

    Claude produces the first pass; you own the judgement that follows. Research at Two Scales: Web search — straightforward factual queries answered in one or two lookups; Research mode — multiple searches that build on each other; cited findings; bigger multi-source jobs.

  • Supporting Solution Design, Development and Iteration

    Solution iteration improves a deliverable over several rounds, with Claude as the drafting partner. A solution here is a process, template, piece of guidance, scheme, service design, form or plan — never software.

  • Integrating Claude into Existing Workflows

    Integration here asks where in an existing process a person brings work to Claude. It never means a technical connection between systems.

  • Communicating Value and Limitations to Stakeholders

    Say what is true, including the parts that are not impressive. The report serves two audiences: the enthusiast and the sceptic.

Domain 5: Configuration & knowledge management · 12%

  • Configuring Projects with Instructions and Knowledge Sources

    A Project has two configurable halves: Custom instructions, Project knowledge; Instructions answer “how should this work be done?” Knowledge answers “what should it be done from?”.

  • Managing Uploaded Knowledge and Connectors

    A Project’s knowledge arrives by one of two routes. The choice turns on how the material changes. Upload, Connector.

  • Creating Effective System-Level Instructions

    System-level instructions are standing rules written in plain English. They live in one of three places: Account-wide, Project-level, Organisation-level.

  • Informing, Maintaining, and Updating Configurations

    Keeping a configuration right has three duties: inform, maintain and update. Three Ways a Good Setup Decays: Knowledge goes stale — an uploaded file is a snapshot; nothing announces that its source was superseded; Instructions go out of date — they apply to every chat whether or not the world they describe still exists; Scope creeps — a Project that works attracts neighbouring work; each addition dilutes instructions written for the original job.

Domain 6: Governance, risk & responsible use · 15%

  • Identifying Appropriate and Inappropriate Use Cases

    Two questions decide whether a task goes to Claude. Fit (Domain 4) asks whether Claude would do the work well. Appropriateness asks whether the task should be handed over at all.

  • Applying Data Sensitivity, Regulatory and Privacy Considerations

    Sensitive material is anything an organisation should not hand to an outside service without a decision. A safeguard changes what leaves the organisation’s hands.

  • Following Organisational AI Policies and Governance Standards

    The rule is short: use the workspace your organisation provides. Why the Sanctioned Workspace Is Substance: When an organisation provides Claude, the arrangement governs how its data is handled. The customer is Controller; Anthropic is Processor on the customer’s behalf. By default Anthropic will not use inputs or outputs from commercial products to train its models. Agreement, administration and data handling all attach to the sanctioned workspace.

  • Understanding the Ethical Implications of AI Usage

    This objective asks who owns the output, who deserved to know how it was made, and who gets described by it.

Domain 7: Troubleshooting & optimisation · 10%

CCAO-F exam facts

Questions60
Time limit120 minutes
Question formatMultiple-choice and multiple-response
Passing score720 on a scale of 1,000
Exam fee$99 USD
Certification valid for12 months

Study these topics

Skillmarked is independent and not affiliated with Anthropic. The topic list follows the public exam outline; check the official exam page for the current version before you book.