Updated 7 Nov 2026 · 5 min read
On this page
What the Anthropic CCDV-F is and who it is for
The CCDV-F is the exam behind the Claude Certified Developer - Foundations credential. Anthropic aims it at technical professionals who build, integrate and ship production-grade AI solutions with large language models, particularly Claude. That means AI and machine learning engineers, technical leads and senior software engineers who connect business requirements to working code.
Anthropic recommends, but does not require, one to five years of software engineering experience, at least six months of hands-on work with Claude or comparable LLM systems, proficiency in Python or TypeScript, fluency with REST APIs and command line tools, and a working understanding of LLM fundamentals, agents, context management and MCP. There are no mandatory prerequisites or courses, and the credential is awarded on exam performance alone. It is not intended for casual users or for people without hands-on software development experience.
Anthropic also says its certification exams are open to people who work at organisations in the Claude Partner Network, and you register with a company email on a domain in your organisation's partner record.
Anthropic CCDV-F at a glance
| Item | Detail |
|---|---|
| Exam code | CCDV-F |
| Questions | 53 items, multiple choice and multiple response |
| Time allowed | 120 minutes |
| Passing score | 720 on a scaled range of 100 to 1,000 |
| Exam fee | US$125, with any partner tier discount shown at checkout |
| Where you sit it | Pearson VUE, online proctored or at a test centre |
| Certification valid for | 12 months from the date it is awarded |
Each item states how many answers to select. Your score report shows pass or fail with the scaled score and the percentage correct in each domain. The domain figures are guidance only, because the result is based on your total scaled score.
What is on the exam
Applications and integration (33.1%). By far the heaviest domain. It covers Claude API mechanics such as messages, tools, streaming, vision, thinking, caching, batch use and the trade-off between real-time and batch calls. It also covers software engineering foundations such as REST, JSON, asynchronous code and version control, Claude application design across interfaces, configuration management including CLAUDE.md files, settings.json and model version pinning, and requirements and systems life cycle concepts.
Model selection and optimization (16.8%). LLM fundamentals such as tokens, context windows, sampling and non-determinism, thinking modes and effort levels, plus Opus, Sonnet and Haiku use cases, quality, latency and cost trade-offs, breaking changes between model releases, and token budgeting with prompt caching.
Agents and workflows (14.7%). Choosing between a workflow and an agent, supervisor hierarchies and subagents, building with the Claude Agent SDK and hooks, self-hosted versus Anthropic-hosted agents, and common patterns such as tool-use loops, memory and context-window management, including frameworks like Strands, LangGraph and PydanticAI.
Prompt and context engineering (11.0%). Instruction clarity, few-shot examples, system versus user placement, output constraints and iteration, context window management and preventing drift and bloat, subagent context isolation, and output handling with structured output, validation and defensive parsing.
Tools and MCPs (10.6%). Tool use and function calling, writing tool descriptions, error handling, client-side versus server-side tools and approval patterns, MCP server development with resources, tools and prompts, and choosing between built-in tools, custom tools, Skills and MCPs.
Security and safety (8.1%). Prompt injection and jailbreak defence, untrusted input and data leakage, PII handling, guardrail layering, least privilege, hooks that block destructive actions, and managing secrets and API keys.
Claude Code (3.1%). Its core components, including rules, skills, commands, agents and agent memory, session management, slash commands, headless and streaming modes, the CLAUDE.md hierarchy and settings.json.
Eval, testing and debugging (2.6%). Identifying error types, choosing recovery strategies, reading traces for failure modes and isolating whether a problem sits in the integration layer or the model output.
Why people fail it
The weighting is lopsided, and candidates misread it in both directions. Claude Code and evaluation sound central to modern work, yet together they are under 6% of the blueprint. The API and application domain alone is a third of it, so developers who know Claude Code well but have not worked with the Messages API, caching, batch calls and configuration lose the most marks.
The second trap is breadth inside that big domain. It mixes Claude-specific mechanics with ordinary software engineering, such as asynchronous code, REST and version control, so a gap in either half hurts. Skills such as model version pinning and prompt versioning are easy to skip because they are not exciting.
The third is trade-off questions. Many items ask which approach best fits a requirement, such as an overnight batch job where cost matters more than speed, and the plausible wrong answers are all things that would work. Read for the constraint first.
A study plan that fits the exam
Six weeks suits most developers who already use Claude. The plan gives the API and application domain the most time.
- Week 1: API mechanics. Messages, tools, streaming, vision, thinking and the real-time versus batch decision. Take the free CCDV-F practice questions to find your gaps.
- Week 2: application design and configuration. Schema design, session hygiene, CLAUDE.md, settings.json, model version pinning and prompt versioning, plus the engineering basics.
- Week 3: models, tokens and cost. LLM fundamentals, Opus, Sonnet and Haiku trade-offs, token budgeting and prompt caching.
- Week 4: agents and tools. Build a small agent with the Agent SDK, write tool descriptions with error handling, and write a simple MCP server.
- Week 5: prompts, context, security and Claude Code. Few-shot and structured output, context pruning and compaction, prompt injection defences, hooks and secrets, and the Claude Code configuration hierarchy.
- Week 6: timed runs. Work through the questions-only copy in the CCDV-F practice question pack in 120 minute blocks and read the explanation for every miss.
On exam day
After you register and pay, you create a Pearson VUE account and book a slot, either online with a proctor or at a Pearson test centre. You need valid, unexpired government-issued photo ID, and the name on it must match your registration exactly. You may cancel or reschedule up to 24 hours before the appointment, and changes inside 24 hours forfeit the fee.
Before the exam starts you accept a confidentiality agreement covering all exam content. If you test online, you stay in view of the proctor and webcam, and phones, notes, headphones and other materials are not allowed.
Frequently asked questions
What happens if I fail the CCDV-F?
You can retake it after a waiting period that grows with each failed attempt: 14 days after the first, 30 days after the second and 90 days after the third. You can take the exam up to four times in a rolling twelve-month period, and the exam fee applies to each attempt.
Is the practice question pack enough on its own?
No. It is practice, not a course. The 96 questions with explanations show how Anthropic frames developer decisions and where your gaps are, but the CCDV-F assumes you have built with the API and tools. Build a small agent first, then use the questions to check yourself and rehearse under time.
How do I keep the credential?
It is valid for 12 months. To renew on time you review what has changed and complete a free assessment that is not proctored on the Anthropic Partner Academy. If it lapses you must retake the full exam at the full fee, and Anthropic may require a full retake if the exam content changes significantly.
Try the free questions first, then get all 96 CCDV-F practice questions with full explanations for US$39, pass or your money back: get the CCDV-F pack.
Sources
The official pages the facts in this guide were checked against.
- anthropic-partners.skilljar.com/page/partner-certifications
- everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F6nizmqk8tpzpfjvt6qmmav7rh%2Fpublic%2F1783542875%2FClaude+Certified+Developer+%E2%80%93+Foundations+Exam+Guide.pdf
- anthropic-partners.skilljar.com/page/certification-eligibility