CCDV-F·In development
Claude Certified Developer - Foundations
The Claude developer certification, officially the Claude Certified Developer - Foundations (CCDV-F), is Anthropic's foundations exam for engineers building applications on Claude. It covers 8 weighted domains from agents and the Agent SDK to the Claude API, tools and MCP servers, prompt and context engineering, and application security, across 53 questions scored 100 to 1000 with 720 to pass. We are building adaptive prep for it now.
- $125
- exam fee
- 53
- questions
- 120 min
- time limit
- 720
- to pass (of 1000)
- 12 mo
- valid for
What the developer exam tests
The CCDV-F guide weights 8 domains by job-task analysis, so the weightings are fractional. Applications and Integration carries the most, reflecting how much of the developer role is real software engineering around the model.
Domain 1
14.7%Agents and Workflows
- 1.1Agent Architecture (4.5%): Principles, patterns, and tradeoffs of agent and workflow architecture, including the decision criteria for using a workflow versus an agent, the structure of manager/supervisor hierarchies, and the role of subagents in improving task execution.
- 1.2Agent Construction with Claude (5.3%): Methods, tools, and platforms for constructing Claude agents, including the Claude Agent SDK, custom agent loops and harnesses, managed agent deployment models (self-hosted vs. Anthropic-hosted), and hooks for deterministic actions.
- 1.3Agent Patterns and Frameworks (4.9%): Common agent design patterns (tool-use loops, sub-agents, memory, context-window management) and agentic abstraction frameworks (e.g., Strands, LangGraph, PydanticAI) for building agents and workflows for multi-step tasks.
Domain 2
33.1%Applications and Integration
- 2.1Understanding Requirements (3.4%): Functional and infrastructure requirements based on business requirements and solution architecture.
- 2.2Systems Life Cycle (2.8%): Systems life cycle management concepts and frameworks used to develop, implement, operate, and maintain IT systems.
- 2.3Claude API Mechanics (6.8%): Claude API behavior and mechanics, including messages, tools, streaming, vision, thinking, caching, invoking Claude through third-party vendors, Messages API data access patterns, batch API use, and tradeoffs between realtime and batch API selection.
- 2.4Software Engineering Foundations (7.4%): Core software engineering principles and practices, including REST APIs, JSON, asynchronous programming, version control, SDLC integration, code review, and small- and large-scale refactoring.
- 2.5Claude Application Design (8.6%): Design considerations for building Claude applications, including how Claude interprets instructions across interfaces (Claude Code, Desktop, claude.ai, API, SDKs), content boundaries, schema design, session hygiene, and plugin management.
- 2.6Configuration Management (4.1%): Configuration management for Claude system components, including CLAUDE.md files, settings.json, model version pinning, prompt versioning, and plugin dependencies.
Domain 3
3.1%Claude Code
- 3.1Claude Code Operation (3.1%): Claude Code core components (Rules, Skills, Commands, Agents, Agent Memory), features (session management, built-in and custom slash commands, headless mode, streaming mode, auto-mode), the CLAUDE.md hierarchy, repository initialization, and settings.json configuration.
Domain 4
2.6%Eval, Testing, and Debugging
- 4.1Debugging and Error Handling (2.6%): Debugging and error handling techniques for Claude applications, including error type identification, recovery strategy selection, trace analysis to identify failure modes, and problem origin isolation between the integration layer and model output.
Domain 5
16.8%Model Selection and Optimization
- 5.1LLM Fundamentals (5.2%): Basic understanding of LLMs (tokens, context windows, sampling, non-determinism, next-token generation), model options (fast mode, extended thinking, adaptive thinking, effort levels), and fundamental prompting techniques (zero-shot, single-shot, multi-shot).
- 5.2Technical Fundamentals (6.1%): Foundational technical concepts supporting AI application development, including basic engineering practices (integrating with SDKs that wrap REST APIs, websockets).
- 5.3Model Selection and Tradeoffs (2.7%): Claude model capabilities (Opus vs. Sonnet vs. Haiku use cases, adaptive thinking support), tradeoffs across quality/latency/cost parameters, and breaking behavior changes across model releases when selecting models for tasks.
- 5.4Cost and Token Management (2.8%): Token budgeting and cost management techniques for Claude applications, including token usage tracking, cost modeling, and caching techniques (prompt caching, cache check-pointing) for cost optimization.
Domain 6
11%Prompt and Context Engineering
- 6.1Context Engineering (3.8%): Context and memory management techniques for Claude applications, including context window management, prevention of context drift and bloat (tool output pruning, compaction), and context isolation through subagents or multi-step agentic workflows.
- 6.2Prompt Engineering (4.6%): Prompt engineering principles and methods (instruction clarity, few-shot examples, system versus user placement, output constraints, prompt and instruction placement across components, iterative refinement, prompt adjustment, input sanitization) when writing and iterating on prompts for Claude.
- 6.3Output Handling (2.6%): Established patterns and techniques for producing, validating, and consuming Claude output, including structured output patterns, response validation, defensive parsing, and skepticism toward confident output.
Domain 7
8.1%Security and Safety
- 7.1AI Application Security (3.2%): Data privacy and security best practices, including prompt injection awareness and mitigation, jailbreak defense, untrusted input handling, data leakage prevention, PII handling, and ensuring authentication, authorization, confidentiality, privacy, and integrity.
- 7.2Guardrails and Safe Deployment (2.3%): Safe and responsible deployment practices (content policy, guardrail layering) and secure-by-design principles (privacy, identity and access management, least privilege).
- 7.3Claude Hooks (1.0%): Leveraging hooks for guardrails and safety controls to prevent destructive actions within Claude applications.
- 7.4Identity, Secrets, and Key Management (1.6%): Managing secrets, credentials, and API keys across Claude development and production environments, including identity validation and authentication, access approval and level verification, and authorized access monitoring.
Domain 8
10.6%Tools and MCPs
- 8.1Tool Implementation (4.4%): Tool implementation practices for Claude applications, including tool use and function calling, configuration for external system interaction, tool description writing, error handling, tool usage patterns (agentic harness dispatch, client-side vs. server-side tools, approval patterns), and tool set construction best practices.
- 8.2MCP Server Development (2.1%): MCP server development practices, including server authoring, deployment, integration with Claude applications, MCP resources, tools, and prompts, and communication patterns (stdio, sockets, client vs. server).
- 8.3Agentic Customization (4.1%): Tradeoffs among built-in Tools, custom Tools, Skills, and MCPs for selecting and applying the appropriate approach for a given use case.
Claude Certified Developer - Foundations prep is in development
We are building adaptive prep for this exam. Because we track mastery per concept rather than per course, the work you put in on the live Architect Foundations track already counts towards the concepts these exams share, so starting now puts you ahead.
Start with the Architect Foundations trackFrequently asked
- How much does the Claude developer certification cost?
- The CCDV-F exam costs $125, the same as the architect foundations exam, booked through Pearson VUE.
- How is CCDV-F different from the architect exam?
- The developer track is engineering-first: it weights the Claude API, tools and MCP servers, prompt and context engineering, and application security, whereas the architect foundations exam weights system design and orchestration. Both are foundations-level and both cost $125.
- How many questions is the CCDV-F exam?
- 53 questions in 120 minutes, scored 100 to 1000 with 720 to pass. Unlike the architect exam it is not built around a fixed scenario bank; items are written directly against the weighted skills.
- Is the Claude developer certification worth it?
- It is a cheap, verifiable proxy for the skills employers pay a premium for: building reliable applications on Claude. The preparation alone leaves you a measurably better Claude developer, which is the floor most certifications cannot offer.
- When can I prepare for it on AI Skill Certs?
- Developer prep is in active development. Because we track mastery per concept rather than per course, the progress you build on shared concepts carries across every certification we prep. Time spent now is not wasted when you move between tracks. So the fastest way to get ahead today is to start on the architect foundations track, whose shared concepts count towards the developer exam.