CCDV-F exam map — domains, weights and how to use this hive
CCDV-F exam map
This note maps the Claude Certified Developer – Foundations exam onto this hive. For each domain it shows how much of the exam it carries, where it is taught here, and how the mock papers sample it. Every exam fact below comes from the official exam guide, version 1.0 (effective July 2026). Where this hive makes its own choice, such as how many seats a domain gets on a mock paper, the note says so.
Who can take the exam
Anthropic's certification FAQ says: "Certification is currently available only to organizations in the Claude Partner Network." Registration also needs a partner email address on a recognized company domain. Personal email addresses do not work. Check that your organization is in the network before you plan around a date.
The FAQ also lists Claude Certified Developer – Foundations among the exams that count towards Claude Partner Network eligibility, so passing it adds to your organization's standing in the network. The same FAQ lists Claude Certified Associate under the exams that do not count towards that eligibility. If partner-network standing is your goal, this developer credential counts and the Associate one does not.
Registration goes through the Anthropic Partner Academy, and Pearson VUE delivers the exam. The guide states that there are no mandatory prerequisites. It recommends one to five years of software engineering and at least six months of hands-on work with Claude or comparable LLM-based systems, and says that experience is recommended, not required.
The exam at a glance
| What | Exam guide v1.0 |
|---|---|
| Items | 53 |
| Item format | Multiple-choice and multiple-response; each item states how many responses to select |
| Time limit | 120 minutes |
| Delivery | Proctored, online or at a test center, per program policy |
| Passing score | Scaled score of 720 on a scale of 100–1,000 |
| Validity | 12 months from the date the credential is awarded |
The guide sets the fee and the retake rules, and both can change. Check them in the current guide rather than here.
The eight domains
The guide publishes each domain's weight to one decimal place and calls the weights "the approximate proportion of scored items drawn from each domain". The mock-paper seats are this hive's own allocation: the guide's weights rounded to whole points, applied to 53 items and rounded by largest remainder, so the seats always add up to 53.
| Domain | Weight | Skills | Seats per mock (house) |
|---|---|---|---|
| 1 Agents and Workflows | 14.7% | 3 | 8 |
| 2 Applications and Integration | 33.1% | 6 | 17 |
| 3 Claude Code | 3.1% | 1 | 2 |
| 4 Eval, Testing, and Debugging | 2.6% | 1 | 1 |
| 5 Model Selection and Optimization | 16.8% | 4 | 9 |
| 6 Prompt and Context Engineering | 11.0% | 3 | 6 |
| 7 Security and Safety | 8.1% | 4 | 4 |
| 8 Tools and MCPs | 10.6% | 3 | 6 |
Domain 2 carries a third of the exam on its own. Domains 3 and 4 together carry under six percent, so a mock gives them only three seats between them. Spend your time where the weight is, but do not skip the small domains: every skill appears on every paper.
Where each domain is taught
Every domain has:
- a narrated lecture deck for each topic, with a companion quiz;
- flashcards;
- a study note;
- a hands-on code exercise with a reference solution.
| Domain | Topics in this hive |
|---|---|
| 1 Agents | Agent and workflow architecture; Building agents with Claude; Agent patterns and frameworks |
| 2 Applications | Requirements and the systems life cycle; Claude API mechanics; Software engineering foundations; Designing Claude applications; Configuration management |
| 3 Claude Code | Operating Claude Code |
| 4 Eval and debugging | Debugging and error handling |
| 5 Models | LLM fundamentals; Technical fundamentals; Choosing models and managing cost |
| 6 Prompts and context | Context engineering; Prompt engineering and output handling |
| 7 Security | Securing Claude applications; Guardrails, hooks and secrets |
| 8 Tools and MCPs | Implementing tools; MCP servers and agentic customization |
How to use the hive
- Learn a topic. Watch the deck, then take its quiz straight away. The quiz tests only what that deck teaches.
- Consolidate a domain. Read the domain's study note and review its flashcards.
- Apply it. Work through the domain's code exercise, then compare your work with the reference solution. Every exercise can be finished without spending on the API; any optional step that calls the API says so and uses your own key.
- Sit a mock paper once you have covered all eight domains. Take it timed, with no notes.
- Review by domain. Note which domains your missed questions come from. Go back to the decks for your weakest domain, then sit the next paper.
The four mock papers
- Each paper has 53 questions, is timed at 120 minutes, and includes multiple-response items that state how many to select, as the real exam does.
- The four papers share no questions. Every paper asks about all 25 skills, in the seat counts shown above.
- The exam-bank questions are separate from the quiz questions. Scoring well on a paper means applying what you learned to new situations, not recognizing a quiz item you have seen before.
- A mock result is the percentage you answered correctly. It is not the exam's scaled score. The guide reports a pass or fail on a scaled score of 100–1,000 with a cut score of 720. It also reports the percentage correct in each domain, and that per-domain breakdown is the part a mock can imitate.
Staying current
The Claude platform changes faster than the exam. This hive teaches decisions that last: when to cache, how to handle a stop reason, where a credential should live. It avoids prices, rate limits, context-window sizes and model version numbers. When a model, parameter or tool on the platform differs from a deck, trust the documentation page the deck cites, which is linked from the hive's sources.