Exam Prep
Anthropic · CCDV-F

Claude Certified Developer - Foundations

Validates the skills to build, integrate, and ship production-grade applications, agents, and workflows using Claude — covers agents and workflows, API integration, Claude Code, prompt and context engineering, evaluation, model selection, and security.

Start Preparing

Free study references: Pages from Anthropic for every objective

Should I Take the CCDV-F?

You should work towards CCDV-F if you’re aiming for one of these careers:

  • AI engineer / LLM application engineer — integrating Claude into production software through the API and SDKs, including streaming, error handling and multi-format input.
  • Agent or agentic AI engineer — building multi-step agents and workflows with the Claude Agent SDK, custom agent loops and agentic frameworks.
  • Forward-deployed engineer — embedding with a client or business unit to design, build and ship a working Claude-powered solution against their specific requirements.
  • AI solutions / integration engineer — connecting Claude to existing systems through custom tools and MCP servers, and choosing between built-in tools, custom tools, Skills and MCP for a given use case.

The CCDV-F sits inside Anthropic's wider Claude Certification Program, which also includes an Associate track aimed at non-coding users and Architect tracks (Foundations and Professional) aimed at solution design. Earning the Developer credential establishes you in that program without requiring any of the others as a prerequisite.

Is the CCDV-F Worthwhile?

Here’s what we’d tell a friend:

  • It is a new, narrowly scoped credential for a fast-moving role. The exam is built specifically around the Claude API, Claude Agent SDK, Claude Code and MCP rather than general AI knowledge, and the program only started in July 2026, so it targets exactly the skills that current Claude-building job descriptions ask for.
  • Pay figures for the roles it leads to vary enormously by source, seniority and company type. In November 2026, salary trackers put US AI/LLM engineer base pay anywhere from roughly $140,000 at the broad market median to $190,000-$320,000 at the mid-to-senior level at growth-stage companies, with frontier labs and staff-level roles reported well above $400,000 in total compensation. One widely cited agentic-AI-specific figure put average pay for agentic AI roles at about $190,000. These numbers come from different job titles, levels and employers, not a single market rate, and the certification itself does not set any of them — your role and experience do. Source: AI Engineer Salary 2026: $145K–$310K (Real Offer Data), 2026 AI Engineer Compensation Guide, Agentic AI Jobs Grew 280% — But Traditional Developer Hiring Fell 27%: Where Should You Bet Your Career?
  • Demand for the specific skills this exam covers is growing quickly. Trackers of US job postings reported agentic AI roles up roughly 280% year over year to about 90,000 listings in 2026, and one monthly index found MCP mentioned in hundreds of open agentic postings — both core topics on this exam's blueprint. Source: Agentic AI Jobs Grew 280% in 2026 — The Roles, Salaries & Companies Hiring Now, Agentic AI Jobs Index — September 2026 report · Get Ready for Agents
  • Access currently runs through Anthropic's partner structure. The certification sits in Anthropic's Claude Partner Network catalog, so it carries particular weight if you work at, or are evaluated by, a partner organization — candidates there should verify current access and eligibility before registering. Source: Claude Certified Developer Foundations Guide

How Long Will I Have to Spend Studying for the CCDV-F?

The honest answer is that it depends on how much you already know. Anthropic's own description of the candidate says they typically have one to five years of experience in software engineering along with at least six months of hands-on experience with Claude or comparable LLM-based systems, are proficient in Python and/or TypeScript, and are fluent with REST APIs and CLI tools. If that’s your background, you’ve got a good start.

In our plan, you pick the areas of CCDV-F that matter to you — for the exam and for your job — and build a study plan from our domain reviews. Then you take an initial exam, backed by Anthropic’s own documentation, to see where you need to focus to meet your study plan’s goals (our exam review will show you that).

In our store, you can buy a single exam or, if you intend to stick with us, our standard package — which includes, for example, custom drills for the areas our review showed that you need to strengthen (both domain knowledge and exam-taking skills). Repeat with fresh exams, step up to a challenge exam, take advantage of Mentor, and walk into the real exam with your own two-page cheat sheet. See how it works.

How Hard Is the CCDV-F Exam?

Another honest answer: since Anthropic doesn’t publish pass rates, no one knows (including us). What Anthropic does publish: you need a scaled score of 720 or greater to pass. That's on a scale of 100 to 1,000, not a percentage of questions answered correctly. The skills it measures, and how much each area weighs, are listed below.

We can tell you that we update our exams monthly, so they always reflect the current state of both the certification and the documentation that supports it. That means our exams follow the certification’s current topic weights, and our domain reviews and explanations are always up to date.

Start Preparing

We can’t tell you how well you know the content — you need to take one of our real exams for that. But our full exams also tell you how you miss: what question answering habits are tripping you up (and we do it across six kinds of ‘bad habits’). We have over 100 answers written that not only test your knowledge but catch those specific bad habits.

These 10 questions, for example, find which kind of ‘almost right’ answers catch you:

Sample exam coming soon.

Skills at a glance

Agents and Workflows14.7%
  • 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
  • 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
  • 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
Applications and Integration33.1%
  • Functional and infrastructure requirements based on business requirements and solution architecture
  • Systems life cycle management concepts and frameworks used to develop, implement, operate, and maintain IT systems
  • 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
  • Core software engineering principles and practices, including REST APIs, JSON, asynchronous programming, version control, SDLC integration, code review, and small- and large-scale refactoring
  • 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
  • Configuration management for Claude system components, including CLAUDE.md files, settings.json, model version pinning, prompt versioning, and plugin dependencies
Claude Code3.1%
  • 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
Eval, Testing, and Debugging2.6%
  • 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
Model Selection and Optimization16.8%
  • 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)
  • Foundational technical concepts supporting AI application development, including basic engineering practices (integrating with SDKs that wrap REST APIs, websockets)
  • 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
  • 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
Prompt and Context Engineering11%
  • 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
  • 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
  • Established patterns and techniques for producing, validating, and consuming Claude output, including structured output patterns, response validation, defensive parsing, and skepticism toward confident output
Security and Safety8.1%
  • 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
  • Safe and responsible deployment practices (content policy, guardrail layering) and secure-by-design principles (privacy, identity and access management, least privilege)
  • Leveraging hooks for guardrails and safety controls to prevent destructive actions within Claude applications
  • 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
Tools and MCPs10.6%
  • 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
  • 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)
  • Tradeoffs among built-in Tools, custom Tools, Skills, and MCPs for selecting and applying the appropriate approach for a given use case

Domains

Agents and Workflows14.7%
Agent Architecture
  • 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
Agent Construction with Claude
  • 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
Agent Patterns and Frameworks
  • 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
Applications and Integration33.1%
Understanding Requirements
  • Functional and infrastructure requirements based on business requirements and solution architecture
Systems Life Cycle
  • Systems life cycle management concepts and frameworks used to develop, implement, operate, and maintain IT systems
Claude API Mechanics
  • 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
Software Engineering Foundations
  • Core software engineering principles and practices, including REST APIs, JSON, asynchronous programming, version control, SDLC integration, code review, and small- and large-scale refactoring
Claude Application Design
  • 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
Configuration Management
  • Configuration management for Claude system components, including CLAUDE.md files, settings.json, model version pinning, prompt versioning, and plugin dependencies
Claude Code3.1%
Claude Code Operation
  • 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
Eval, Testing, and Debugging2.6%
Debugging and Error Handling
  • 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
Model Selection and Optimization16.8%
LLM Fundamentals
  • 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)
Technical Fundamentals
  • Foundational technical concepts supporting AI application development, including basic engineering practices (integrating with SDKs that wrap REST APIs, websockets)
Model Selection and Tradeoffs
  • 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
Cost and Token Management
  • 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
Prompt and Context Engineering11%
Context Engineering
  • 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
Prompt Engineering
  • 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
Output Handling
  • Established patterns and techniques for producing, validating, and consuming Claude output, including structured output patterns, response validation, defensive parsing, and skepticism toward confident output
Security and Safety8.1%
AI Application Security
  • 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
Guardrails and Safe Deployment
  • Safe and responsible deployment practices (content policy, guardrail layering) and secure-by-design principles (privacy, identity and access management, least privilege)
Claude Hooks
  • Leveraging hooks for guardrails and safety controls to prevent destructive actions within Claude applications
Identity, Secrets, and Key Management
  • 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
Tools and MCPs10.6%
Tool Implementation
  • 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
MCP Server Development
  • 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)
Agentic Customization
  • Tradeoffs among built-in Tools, custom Tools, Skills, and MCPs for selecting and applying the appropriate approach for a given use case