Claude Certified Developer (Foundations)

Build production Claude applications, agents, and tools.

Accumentum’s Claude Certified Developer (Foundations) training prepares software engineers to integrate the Claude API, design agents and workflows, implement tools and MCP servers, manage models and cost, and ship reliable Claude-powered applications aligned to the official CCDV-F exam.

Aligned to the official CCDV-F exam. Covers all eight domains with heavy emphasis on Applications & Integration (33.1%), Model Selection & Optimization, Agents & Workflows, Tools & MCPs, and more.

What you will gain

Claude Developer

Foundations-level capability to build, integrate, and ship Claude applications and agents.

01

API & application design

Master Claude API mechanics, streaming, caching, structured outputs, and application architecture.

02

Agents & tools

Build agent loops, subagents, custom tools, and MCP servers with the Agent SDK.

03

Production readiness

Apply security, evaluation, debugging, model selection, and cost optimization practices.

About the Course

Hands-on Claude developer training designed for the Claude Certified Developer (Foundations) exam.

This Accumentum course prepares software engineers and technical builders to design, implement, and ship production-grade applications and agents using the Claude API, Agent SDK, tools, MCP, and Claude Code.

The Claude Certified Developer, Foundations (CCDV-F) credential validates that you can build, integrate, and ship Claude-powered applications and agents. It is the builder track in Anthropic’s role-based certification program and is intended for engineers who work with the Claude API, SDKs, Agent SDK, tools, and Model Context Protocol.

Accumentum’s training maps directly to the official exam blueprint. You will practice Claude API mechanics, application design, agent architecture and construction, tool and MCP implementation, prompt and context engineering, model selection and cost management, security and safety patterns, Claude Code operation, and evaluation and debugging techniques that mirror real engineering work.

Whether you are integrating Claude into existing systems, building new agentic products, or preparing for the CCDV-F exam, this course develops the practical engineering judgment required of a Claude Certified Developer.

Why Accumentum

Why engineers choose Accumentum for Claude Developer preparation.

01

Exam-aligned curriculum

Full coverage of all eight CCDV-F domains with weighted emphasis on Applications & Integration (33.1%) and Model Selection & Optimization.

02

Builder-focused practice

Hands-on exercises covering API integration, agent construction, tool design, MCP servers, and production patterns.

03

CareerSync® guidance

Pathway support that connects your engineering experience, target role, and funding options to the right Claude credential.

04

Production outcomes

Training designed for engineers who ship: API design, configuration management, security, evals, and cost control.

Who Should Enroll

Built for engineers who build with the Claude API and Agent SDK.

Ideal for

  • Software engineers integrating Claude into applications and services
  • Developers building agents, tools, and MCP servers
  • Engineers working with the Claude API, Agent SDK, and Claude Code
  • Technical contributors preparing for the CCDV-F exam
  • Teams shipping production Claude features who need validated skills

You will learn to

  • Design and implement Claude applications using the Messages API, tools, streaming, and caching
  • Build agent architectures, subagents, and workflows with the Agent SDK
  • Implement custom tools and MCP servers for agentic systems
  • Select models, manage tokens and cost, and apply security guardrails
  • Debug, evaluate, and optimize Claude-powered systems in production
Curriculum

Mapped to the official Claude Certified Developer (Foundations) exam domains.

Each module aligns to the CCDV-F content outline so you build exactly the skills measured on the proctored exam.

Course Features

Designed for practical Claude Developer training and CCDV-F exam readiness.

Interactive Learning

Engage in guided practice, code-oriented exercises, and realistic integration scenarios with experienced instructors.

Exam-Focused Practice

Work through domain-weighted exercises that mirror the engineering judgment and tasks tested on the official exam.

Study Resources

Access structured materials, checklists, and review tools aligned to the eight CCDV-F domains.

Certification Guidance

Receive clear direction on exam format, scoring, registration, and how to approach the proctored assessment.

Certification Exam

Prepare for the official Claude Certified Developer, Foundations (CCDV-F) exam.

CCDV-F Exam Readiness

Accumentum’s training prepares you to demonstrate hands-on Claude development capability across all eight official domains, with special focus on the highest-weighted skills: Applications & Integration, Model Selection & Optimization, Agents & Workflows, and Tools & MCPs.

Claude Certified Developer Foundations Certification Badge

The Claude Certified Developer (Foundations) exam (CCDV-F) is a 53-question, 120-minute proctored assessment. It validates that you can build, integrate, and ship production-grade Claude applications and agents using the Claude API, Agent SDK, tools, MCP, and Claude Code.

Passing the exam demonstrates that you can design applications, implement agents and workflows, select and optimize models, engineer prompts and context, implement tools and MCP servers, apply security practices, operate Claude Code, and debug and evaluate Claude systems.

Earning the Developer Foundations credential positions you as a capable Claude engineer ready to deliver production AI features with confidence and accountability.

Exam Blueprint

Every CCDV-F domain and skill.

Anthropic's exam guide for CCDV-F (version 1.0, effective July 2026) lists 8 content domains and 25 skills. We've copied every one below in Anthropic's own wording, with the weight Anthropic gives each domain. Our lessons and labs follow the same outline.

Domain 1: Agents and Workflows (14.7%)

  • Agent 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.
  • Agent 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.
  • Agent Patterns and Frameworks (4.9%). Common agent design patterns (tool-use loops, sub-agents, memory, context-window management) and agentic abstraction frameworks (for example Strands, LangGraph, PydanticAI) for building agents and workflows for multi-step tasks.

Domain 2: Applications and Integration (33.1%)

  • Understanding Requirements (3.4%). Functional and infrastructure requirements based on business requirements and solution architecture.
  • Systems Life Cycle (2.8%). Systems life cycle management concepts and frameworks used to develop, implement, operate, and maintain IT systems.
  • Claude 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.
  • Software 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.
  • Claude 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.
  • Configuration 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: Claude Code (3.1%)

  • Claude 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: Eval, Testing, and Debugging (2.6%)

  • Debugging 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: Model Selection and Optimization (16.8%)

  • LLM 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).
  • Technical Fundamentals (6.1%). Foundational technical concepts supporting AI application development, including basic engineering practices (integrating with SDKs that wrap REST APIs, websockets).
  • Model 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.
  • Cost 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: Prompt and Context Engineering (11.0%)

  • Context 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.
  • Prompt 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.
  • Output 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: Security and Safety (8.1%)

  • AI 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.
  • Guardrails 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).
  • Claude Hooks (1.0%). Leveraging hooks for guardrails and safety controls to prevent destructive actions within Claude applications.
  • Identity, 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: Tools and MCPs (10.6%)

  • Tool 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.
  • MCP 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).
  • Agentic 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.
Who It Is For

The CCDV-F candidate profile.

Here's how Anthropic describes the audience. The certification is intended for technical professionals who build, integrate, and ship production-grade AI solutions using large language models (LLMs), particularly Anthropic's Claude platform. This audience primarily includes AI and machine learning engineers, technical leads, and senior software engineers operating at the intersection of business requirements and technical implementation. These professionals 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. They possess strong foundational knowledge and applied skills in software development, with the ability to build agents and workflows using the Claude Agent SDK and agentic frameworks, integrate Claude through the Application Programming Interface (API) and client Software Development Kits (SDKs), operate Claude Code for codebase modernization, write effective prompts and apply context engineering, design and run evals, and build custom tools and Model Context Protocol (MCP) servers. They understand tradeoffs in model selection and tool type and can apply appropriate patterns to meet technical requirements. They are proficient in Python and/or TypeScript, fluent with REST APIs and Command Line Interface (CLI) tools, and have a working understanding of LLM fundamentals, agents, context management, and MCP. This certification is not intended for non-technical or casual users of Claude-based applications, or individuals without hands-on software development experience. It also excludes roles limited to prompt writing or other isolated tasks without broader application development responsibility.

Recommended experience

  • One to five years of experience in software engineering
  • At least six months of hands-on experience with Claude or comparable LLM-based systems
  • Proficiency in Python and/or TypeScript
  • Fluency with REST APIs and CLI tools
  • Working understanding of LLM fundamentals, agents, context management, and MCP

About prerequisites, Anthropic says: There are no mandatory prerequisites or courses required to sit this exam. The experience above is recommended, not required. The credential is awarded based on exam performance alone.

Exam Format

How the CCDV-F exam is built.

Exam details

  • Exam code: CCDV-F
  • Number of items: 53
  • Item format: multiple-choice and multiple-response items, and each item tells you how many responses to select
  • Time limit: 120 minutes
  • Delivery: proctored online or at a Pearson VUE test center
  • Passing score: a scaled score of 720 on a scale of 100 to 1,000
  • Exam fee: $125 USD
  • Validity: 12 months from the date the credential is awarded
  • Results: pass or fail with a scaled score, plus your percent correct in each domain

The exam is criterion referenced. You're measured against a fixed standard set by subject matter experts, not against other candidates. Your domain percentages help you see where you were strong or weak, but only the total scaled score decides pass or fail.

Study Plan

Turning the CCDV-F outline into a plan.

We start with Agents and Workflows, which Anthropic weights at 14.7%. It has 3 skills in the guide, and each one gets a lesson plus a short lab.

Next we cover Applications and Integration, worth about 33.1% of the exam. It has 6 skills in the guide, and each one gets a lesson plus a short lab.

Then we move to Claude Code, at roughly 3.1% of scored items. It has 1 skill in the guide, and each one gets a lesson plus a short lab.

After that comes Eval, Testing, and Debugging, which makes up about 2.6%. It has 1 skill in the guide, and each one gets a lesson plus a short lab.

We follow with Model Selection and Optimization, which Anthropic weights at 16.8%. It has 4 skills in the guide, and each one gets a lesson plus a short lab.

Then it's Prompt and Context Engineering, worth about 11.0% of the exam. It has 3 skills in the guide, and each one gets a lesson plus a short lab.

We also work through Security and Safety, at roughly 8.1% of scored items. It has 4 skills in the guide, and each one gets a lesson plus a short lab.

We wrap up with Tools and MCPs, which makes up about 10.6%. It has 3 skills in the guide, and each one gets a lesson plus a short lab.

Applications and Integration carries the most weight at 33.1%, so it gets the most lab time. In the final week you work the sample questions in Anthropic's guide, then retest the domains where you were weakest.

How Anthropic Says to Prepare

Anthropic's own CCDV-F prep advice.

Anthropic says there's no single required course and no resource guarantees a pass. Its guide recommends these steps, and we build our labs around them.

From the official exam guide

  • Study the exam blueprint and self-assess against each objective
  • Review official Anthropic documentation for the Claude API, models, prompt engineering, Claude Code, Skills, and MCP
  • Build and operate at least one Claude application that exercises the API, integrates one or more tools, applies basic prompt and context engineering, and includes simple security and evaluation practices
  • Practice the developer competencies: writing prompts and system instructions, building agents and workflows, configuring Claude Code, managing tokens and cost, implementing guardrails, and creating custom tools or MCP servers
  • Complete the sample questions in the guide to familiarize yourself with item style
Exam Policies

What to know before you book CCDV-F.

You register through the Anthropic Partner Academy and schedule with Pearson VUE, either online or at a test center. You can cancel or reschedule up to 24 hours before your appointment. Changes inside 24 hours forfeit the exam fee, and so does a no-show.

Bring a valid, unexpired, government-issued photo ID, and make sure the name matches your registration exactly. Accommodations have to be requested and approved by Pearson VUE before you schedule.

If you don't pass, the waits grow with each attempt: 14 days after the first, 30 days after the second and 90 days after the third. You can take an exam up to four times in a rolling 12-month period, and the fee applies to every attempt.

The Claude Certified Developer Foundations credential is valid for 12 months. To renew on time, you review what's changed and complete a free, non-proctored assessment on the Anthropic Partner Academy. If it lapses, you retake the full exam at the full fee.

Career Outlook

Where CCDV-F can take you.

Per the U.S. Bureau of Labor Statistics, software developers, quality assurance analysts and testers earned a median annual wage of $134,040 in May 2025. That figure is a national midpoint. Where you live, how long you have been in the field and who you work for all move the number. Source: BLS Occupational Outlook Handbook.

Funding

Ways to pay for CCDV-F training.

Our funding page lists the ways to pay for training, including employer sponsorship. If you'd like help picking the right Claude track, talk with us or email info@accumentum.net.

Frequently Asked Questions

Understand how Accumentum’s Claude Certified Developer (Foundations) training supports exam preparation, practical engineering skills, eligibility, and career impact.

Enrollment

Enroll in Claude Certified Developer (Foundations) training with Accumentum.

Enroll in Accumentum’s Claude Certified Developer (Foundations) Certification Training Course to build the engineering skills needed to integrate the Claude API, design agents and workflows, implement tools and MCP servers, manage models and cost, and ship reliable Claude applications. Those are exactly the capabilities measured by the official CCDV-F exam.

You will gain confidence designing production integrations, constructing agents, applying security and evaluation practices, and optimizing for quality and cost.

This course is your direct pathway to the Claude Certified Developer (Foundations) credential and a stronger foundation for future Claude Architect certifications. For current schedules, pricing, and registration, visit Accumentum’s registration page.

Advance your Claude engineering capability with Developer Foundations training.

Prepare for the Claude Certified Developer, Foundations (CCDV-F) exam, build production Claude applications and agents, and learn API integration, agent design, tools, MCP, model optimization, and security practices with confidence.