Work at a Claude Partner Network organization
RequiredRegister with your organization's recognized company email domain. You must be 18 or older.
Claude Certified Developer – Foundations (CCDV-F) Exam Guide
Validates knowledge of building production Claude applications, including API integration, agents, tools and MCP, prompt and context engineering, evals, security and cost.
The exam tests whether you can build and ship Claude applications: which API feature, agent pattern, tool type, model or guardrail fits a requirement, and why. Use the exam guide as your syllabus, take Anthropic's free prep course, build a small Claude application yourself and finish with exam-level practice questions.
Understand the exam
Syllabus
1Agents and workflows14.7%
- Agent architecture (4.5%): when to use a workflow or an agent, supervisor hierarchies and the role of subagents
- Agent construction with Claude (5.3%): the Agent SDK, custom agent loops and harnesses, self-hosted versus Anthropic-hosted agents, and hooks for deterministic actions
- Agent patterns and frameworks (4.9%): tool-use loops, sub-agents, memory and context-window management, and frameworks such as Strands, LangGraph and PydanticAI
2Applications and integration33.1%
- Understanding requirements (3.4%): turn business requirements and solution architecture into functional and infrastructure requirements
- Systems life cycle (2.8%): concepts and frameworks for developing, operating and maintaining systems
- Claude API mechanics (6.8%): messages, tools, streaming, vision, thinking, caching, third-party platforms, and real-time versus batch use
- Software engineering foundations (7.4%): REST APIs, JSON, async programming, version control, code review and refactoring
- Claude application design (8.6%): how Claude reads instructions across interfaces, content boundaries, schema design, session hygiene and plugins
- Configuration management (4.1%): CLAUDE.md, settings.json, model version pinning, prompt versioning and plugin dependencies
3Claude Code3.1%
- Claude Code operation (3.1%): rules, skills, commands, agents and memory, session management, headless mode, the CLAUDE.md hierarchy and settings.json
4Eval, testing and debugging2.6%
- Debugging and error handling (2.6%): identify error types, choose recovery strategies, use trace analysis and isolate integration faults from model output
5Model selection and optimization16.8%
- LLM fundamentals (5.2%): tokens, context windows, sampling, non-determinism, thinking and effort options, and zero-, single- and multi-shot prompting
- Technical fundamentals (6.1%): integrating with SDKs that wrap REST APIs and websockets
- Model selection and tradeoffs (2.7%): Opus, Sonnet and Haiku use cases, quality, latency and cost tradeoffs, and behavior changes across releases
- Cost and token management (2.8%): token tracking, cost modeling and prompt caching
6Prompt and context engineering11.0%
- Context engineering (3.8%): context window management, preventing drift and bloat with pruning and compaction, and context isolation through subagents
- Prompt engineering (4.6%): instruction clarity, few-shot examples, system versus user placement, output constraints, iteration and input sanitization
- Output handling (2.6%): structured output, response validation, defensive parsing and skepticism toward confident output
7Security and safety8.1%
- AI application security (3.2%): prompt injection, jailbreak defense, untrusted input, data leakage and PII handling
- Guardrails and safe deployment (2.3%): content policy, guardrail layering, least privilege and secure-by-design
- Claude hooks (1.0%): hooks as guardrails that prevent destructive actions
- Identity, secrets and key management (1.6%): managing credentials and API keys, authentication and access monitoring
8Tools and MCPs10.6%
- Tool implementation (4.4%): tool use and function calling, tool descriptions, error handling, client-side versus server-side tools and approval patterns
- MCP server development (2.1%): server authoring, resources, tools and prompts, and stdio and socket communication
- Agentic customization (4.1%): tradeoffs among built-in tools, custom tools, Skills and MCP for a given use case
Official exam guide · Version 1.0, July 2026
Format
- Questions
- 53
- Duration
- 2h
- Passing score
- 720 / 1000
- Delivery
- Test centre or online
- Languages
- English
Question types
Choose the single best answer.
CertUp example
An application resends the same 5,000-token policy document with every request, and input costs keep rising. Which change reduces cost the most without changing behavior?
Show answer
B. Prompt caching reuses the repeated prefix at a lower cost. Temperature does not affect input cost, moving the text changes nothing about its size, and batching suits non-urgent work, not an interactive app.
Select the stated number of correct answers from the list.
CertUp example
Select TWO controls that best limit the damage from prompt injection in an agent that reads web pages.
Show answer
A and B. Isolating untrusted input and gating sensitive actions are enforceable controls; a polite instruction is not, and temperature does not affect injection.
Eligibility and booking
Sign in to the Anthropic Partner Academy with your partner company email, register and pay, then schedule with Pearson VUE. Your registration stays valid for 5 years.
Make a study plan
Read the exam guide first, including its blueprint and sample questions, and mark the domains you use least.
Plan for 15–45 hours. Plan for the low end if you already ship Claude applications with the API, Agent SDK and MCP; plan for the high end if you have used Claude for about six months but not all of the exam domains. The five official prep courses alone run about 13 hours.
- 1Understand the examRead the syllabus and format, check you’re eligible and pick a target date.2 h
- 3Learn the core conceptsWork through one main course or book, topic by topic.17 h
- 4Practice with mock examsTake timed practice tests and review every mistake.9 h
- 5Prepare for exam dayBook the exam and check the ID and delivery rules.2 h
Learn the core concepts
Anthropic's free prep course has five lessons. The two middle lessons map most directly to the heaviest domains.
Build a small application Anthropic's exam guide recommends building and operating at least one Claude application that uses the API and a tool, with basic prompt and context engineering, security and evaluation.
Practice with mock exams
Start with the official sample questions, then use exam-level question sets and review why each wrong option loses.
CCDV-F Exam Guide sample questions
CCDV-F Practice Questions
Claude Certified Developer Foundations mock examAre you ready?
- You can explain why each wrong option in a practice question is worse, not just which one is right
- You can choose between batch and real-time calls, and between built-in tools, custom tools, Skills and MCP, for a given need
- You can name the control that stops a prompt injection from triggering a sensitive action
Prepare for exam day
Use the checklist for your delivery route.
Before testing from home
Before travelling to the test centre
- Run the OnVUE system test on the computer and network you will use
- Clear your desk and keep phones, extra monitors, notes and AI tools out of reach
- Stay in webcam view for the whole session
- Arrive early to check in
- Bring a valid government photo ID whose name exactly matches your registration
- Plan for about 135 minutes in total, including check-in
- Reschedule or cancel in your Pearson VUE account at least 48 hours before your appointment. Later changes or a missed appointment forfeit the exam fee
- If you fail, wait 14 days before the second attempt, 30 before the third and 90 before the fourth, with up to 4 attempts in 12 months
Advice from exam takers
Build with the API, not just the docs
Passers call the exam very hands-on and say it is hard without writing code against the Claude API, building an MCP server and using Claude Code. Anthropic's guide gives the same advice.