Claude Certified Architect (Foundations)

Design production agent systems with Claude.

Accumentum’s Claude Certified Architect (Foundations) training prepares solution architects to design agentic systems, orchestrate multi-agent workflows, integrate tools and MCP servers, configure Claude Code, and deliver reliable structured outputs aligned to the official CCAR-F exam.

Aligned to the official CCAR-F exam. Covers all five domains with emphasis on Agentic Architecture & Orchestration (27%), Claude Code Configuration, Prompt Engineering & Structured Output, Tool Design & MCP, and Context Management.

What you will gain

Claude Architect

Foundations-level capability to design and architect reliable Claude agent systems.

01

Agentic architecture

Design agent loops, multi-agent orchestration, hooks, and production workflow patterns.

02

Tools & MCP

Design effective tool interfaces and integrate Model Context Protocol servers.

03

Reliable systems

Configure Claude Code, engineer structured outputs, and manage context for production reliability.

About the Course

Solution-architecture training designed for the Claude Certified Architect (Foundations) exam.

This Accumentum course prepares solution architects and technical leaders to design agentic systems, orchestrate multi-agent workflows, integrate tools and MCP, configure Claude Code, and deliver reliable structured outputs in production.

The Claude Certified Architect, Foundations (CCAR-F) credential validates that practitioners can design and architect reliable, production-grade agent systems using Claude. It is the foundations-level architect track in Anthropic’s role-based certification program and is intended for solution architects with hands-on experience building on the Claude API, Agent SDK, Claude Code, and Model Context Protocol.

Accumentum’s training maps directly to the official exam blueprint. You will practice agentic architecture and orchestration, tool design and MCP integration, Claude Code configuration and workflows, prompt engineering and structured output patterns, and context management and reliability techniques that mirror real architectural decisions.

Whether you are designing multi-agent systems, integrating MCP tools, configuring team workflows with Claude Code, or preparing for the CCAR-F exam, this course develops the architectural judgment required of a Claude Certified Architect.

Why Accumentum

Why architects choose Accumentum for Claude Architect preparation.

01

Exam-aligned curriculum

Full coverage of all five CCAR-F domains with weighted emphasis on Agentic Architecture & Orchestration (27%) and production reliability.

02

Architecture-focused practice

Scenario-based exercises covering multi-agent design, tool/MCP integration, Claude Code workflows, and structured output patterns.

03

CareerSync® guidance

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

04

Production outcomes

Training designed for architects who design systems that ship: orchestration, reliability, context management, and tool boundaries.

Who Should Enroll

Built for solution architects who design Claude agent systems.

Ideal for

  • Solution architects designing agentic systems with the Claude Agent SDK
  • Technical leads configuring Claude Code and MCP integrations for teams
  • Architects with hands-on experience building multi-agent workflows
  • Practitioners preparing for the official CCAR-F exam
  • Teams delivering production Claude solutions who need validated architecture skills

You will learn to

  • Design agentic loops, multi-agent orchestration, and production workflow patterns
  • Design effective tool interfaces and integrate MCP servers
  • Configure Claude Code hierarchies, skills, slash commands, and CI/CD workflows
  • Engineer prompts and structured outputs with validation and retry patterns
  • Manage context, escalation, and reliability across long-running agent systems
Curriculum

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

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

Course Features

Designed for practical Claude Architect training and CCAR-F exam readiness.

Interactive Learning

Engage in guided practice, architecture scenarios, and realistic multi-agent design exercises with experienced instructors.

Exam-Focused Practice

Work through domain-weighted, scenario-based exercises that mirror the architectural judgment tested on the official exam.

Study Resources

Access structured materials, checklists, and review tools aligned to the five CCAR-F domains.

Certification Guidance

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

Certification Exam

Prepare for the official Claude Certified Architect, Foundations (CCAR-F) exam.

CCAR-F Exam Readiness

Accumentum’s training prepares you to demonstrate architectural capability across all five official domains, with special focus on the highest-weighted skills: Agentic Architecture & Orchestration (27%), Claude Code Configuration, Prompt Engineering & Structured Output, Tool Design & MCP, and Context Management.

Claude Certified Architect Foundations Certification Badge

The Claude Certified Architect (Foundations) exam (CCAR-F) is a 60-question, 120-minute scenario-based proctored assessment. It validates that you can design and architect reliable production agent systems using the Claude Agent SDK, tools, MCP, Claude Code, and structured output patterns.

Passing the exam demonstrates that you can design agentic architecture and orchestration, implement tool and MCP integrations, configure Claude Code workflows, engineer prompts and structured outputs, and manage context and reliability in production systems.

Earning the Architect Foundations credential positions you as a capable Claude solution architect ready to design production AI systems with confidence and accountability.

Exam Blueprint

What Anthropic says CCAR-F measures.

Anthropic's exam guide for CCAR-F (version 1.0, effective July 2026) lists 5 content domains and 30 task statements. 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: Agentic Architecture & Orchestration (27%)

  • 1.1 Design and implement agentic loops for autonomous task execution
  • 1.2 Orchestrate multi-agent systems with coordinator-subagent patterns
  • 1.3 Configure subagent invocation, context passing, and spawning
  • 1.4 Implement multi-step workflows with enforcement and handoff patterns
  • 1.5 Apply Agent SDK hooks for tool call interception and data normalization
  • 1.6 Design task decomposition strategies for complex workflows
  • 1.7 Manage session state, resumption, and forking

Domain 2: Tool Design & MCP Integration (18%)

  • 2.1 Design effective tool interfaces with clear descriptions and boundaries
  • 2.2 Implement structured error responses for MCP tools
  • 2.3 Distribute tools appropriately across agents and configure tool choice
  • 2.4 Integrate MCP servers into Claude Code and agent workflows
  • 2.5 Select and apply built-in tools (Read, Write, Edit, Bash, Grep, Glob) effectively

Domain 3: Claude Code Configuration & Workflows (20%)

  • 3.1 Configure CLAUDE.md files with appropriate hierarchy, scoping, and modular organization
  • 3.2 Create and configure custom slash commands and skills
  • 3.3 Apply path-specific rules for conditional convention loading
  • 3.4 Determine when to use plan mode vs direct execution
  • 3.5 Apply iterative refinement techniques for progressive improvement
  • 3.6 Integrate Claude Code into CI/CD pipelines

Domain 4: Prompt Engineering & Structured Output (20%)

  • 4.1 Design prompts with explicit criteria to improve precision and reduce false positives
  • 4.2 Apply few-shot prompting to improve output consistency and quality
  • 4.3 Enforce structured output using tool use and JSON schemas
  • 4.4 Implement validation, retry, and feedback loops for extraction quality
  • 4.5 Design efficient batch processing strategies
  • 4.6 Design multi-instance and multi-pass review architectures

Domain 5: Context Management & Reliability (15%)

  • 5.1 Manage conversation context to preserve critical information across long interactions
  • 5.2 Design effective escalation and ambiguity resolution patterns
  • 5.3 Implement error propagation strategies across multi-agent systems
  • 5.4 Manage context effectively in large codebase exploration
  • 5.5 Design human review workflows and confidence calibration
  • 5.6 Preserve information provenance and handle uncertainty in multi-source synthesis
Exam Scenarios

The six CCAR-F scenarios.

Every CCAR-F question sits inside a realistic production scenario. Anthropic picks 4 of these 6 at random for each exam, so we run labs on all six.

Scenario 1: Customer Support Resolution Agent

You are building a customer support resolution agent using the Claude Agent SDK. The agent handles high-ambiguity requests like returns, billing disputes, and account issues. It has access to your backend systems through custom Model Context Protocol (MCP) tools (get_customer, lookup_order, process_refund, escalate_to_human). Your target is 80%+ first-contact resolution while knowing when to escalate.

Primary domains: Agentic Architecture & Orchestration, Tool Design & MCP Integration, Context Management & Reliability

Scenario 2: Code Generation with Claude Code

You are using Claude Code to accelerate software development. Your team uses it for code generation, refactoring, debugging, and documentation. You need to integrate it into your development workflow with custom slash commands, CLAUDE.md configurations, and understand when to use plan mode vs direct execution.

Primary domains: Claude Code Configuration & Workflows, Context Management & Reliability

Scenario 3: Multi-Agent Research System

You are building a multi-agent research system using the Claude Agent SDK. A coordinator agent delegates to specialized subagents: one searches the web, one analyzes documents, one synthesizes findings, and one generates reports. The system researches topics and produces comprehensive, cited reports.

Primary domains: Agentic Architecture & Orchestration, Tool Design & MCP Integration, Context Management & Reliability

Scenario 4: Developer Productivity with Claude

You are building developer productivity tools using the Claude Agent SDK. The agent helps engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate code, and automate repetitive tasks. It uses the built-in tools (Read, Write, Bash, Grep, Glob) and integrates with Model Context Protocol (MCP) servers.

Primary domains: Tool Design & MCP Integration, Claude Code Configuration & Workflows, Agentic Architecture & Orchestration

Scenario 5: Claude Code for Continuous Integration

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.

Primary domains: Claude Code Configuration & Workflows, Prompt Engineering & Structured Output

Scenario 6: Structured Data Extraction

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.

Primary domains: Prompt Engineering & Structured Output, Context Management & Reliability

Who It Is For

The CCAR-F candidate profile.

Here's how Anthropic describes the target candidate. The ideal candidate for this certification is a solution architect who designs and implements production applications with Claude. This candidate has hands-on experience with:

Hands-on experience Anthropic expects

  • Building agentic applications using the Claude Agent SDK, including multi-agent orchestration, subagent delegation, tool integration, and lifecycle hooks
  • Configuring and customizing Claude Code for team workflows using CLAUDE.md files, Agent Skills, MCP server integrations, and plan mode
  • Designing Model Context Protocol (MCP) tool and resource interfaces for backend system integration
  • Engineering prompts that produce reliable structured output, leveraging JSON schemas, few-shot examples, and extraction patterns
  • Managing context windows effectively across long documents, multi-turn conversations, and multi-agent handoffs
  • Integrating Claude into CI/CD pipelines for automated code review, test generation, and pull request feedback
  • Making sound escalation and reliability decisions, including error handling, human-in-the-loop workflows, and self-evaluation patterns

The candidate typically has 6+ months of practical experience building with Claude APIs, Agent SDK, Claude Code, and MCP, understanding both the capabilities and limitations of large language models in production environments.

There's no formal prerequisite course. We still recommend building with the API, the Agent SDK and Claude Code before you book.

Exam Format

CCAR-F at a glance.

Exam details

  • Exam code: CCAR-F
  • Number of items: 60
  • Item format: multiple-choice and multiple-response items, and each item tells you how many responses to select
  • Structure: 4 scenarios drawn at random from a bank of 6
  • 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

A practical path to CCAR-F.

We start with Agentic Architecture & Orchestration, which Anthropic weights at 27%. It has 7 task statements in the guide, and each one gets a lesson plus a short lab.

Next we cover Tool Design & MCP Integration, worth about 18% of the exam. It has 5 task statements in the guide, and each one gets a lesson plus a short lab.

Then we move to Claude Code Configuration & Workflows, at roughly 20% of scored items. It has 6 task statements in the guide, and each one gets a lesson plus a short lab.

After that comes Prompt Engineering & Structured Output, which makes up about 20%. It has 6 task statements in the guide, and each one gets a lesson plus a short lab.

We wrap up with Context Management & Reliability, which Anthropic weights at 15%. It has 6 task statements in the guide, and each one gets a lesson plus a short lab.

Agentic Architecture & Orchestration carries the most weight at 27%, 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 CCAR-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

  • Build an agent with the Claude Agent SDK: implement a complete agentic loop with tool calling, error handling, and session management. Practice spawning subagents and passing context between them.
  • Configure Claude Code for a real project: set up CLAUDE.md with a configuration hierarchy, create path-specific rules in .claude/rules/, build custom skills with frontmatter options (context: fork, allowed-tools), and integrate at least one MCP server.
  • Design and test MCP tools: write tool descriptions that clearly differentiate similar tools. Implement structured error responses with error categories and retryable flags. Test tool selection reliability with ambiguous requests.
  • Build a structured data extraction pipeline: use tool_use with JSON schemas, implement validation-retry loops, design schemas with optional/nullable fields, and practice batch processing with the Message Batches API.
  • Practice prompt engineering techniques: write few-shot examples for ambiguous scenarios. Define explicit review criteria to reduce false positives. Design multi-pass review architectures for large code reviews.
  • Study context management patterns: practice extracting structured facts from verbose tool outputs, implementing scratchpad files for long sessions, and designing subagent delegation to manage context limits.
  • Review escalation and human-in-the-loop patterns: understand when to escalate (policy gaps, customer requests, inability to progress) versus resolve autonomously. Practice designing human review workflows with confidence-based routing.
Exam Policies

How Anthropic runs the CCAR-F exam.

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 Architect 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 CCAR-F can take you.

Per the U.S. Bureau of Labor Statistics, computer network architects earned a median annual wage of $134,050 in May 2025. A median is the midpoint, so half earned more and half earned less, and your own pay will depend on location, experience and employer. Source: BLS Occupational Outlook Handbook.

Funding

Ways to pay for CCAR-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 Architect (Foundations) training supports exam preparation, architectural skill building, eligibility, and career impact.

Enrollment

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

Enroll in Accumentum’s Claude Certified Architect (Foundations) Certification Training Course to build the architectural skills needed to design agentic systems, orchestrate multi-agent workflows, integrate tools and MCP servers, configure Claude Code, and deliver reliable structured outputs. Those are exactly the capabilities measured by the official CCAR-F exam.

You will gain confidence designing production agent architectures, managing context and reliability, applying tool boundaries, and engineering prompts that survive real-world use.

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

Advance your Claude architecture capability with Architect Foundations training.

Prepare for the Claude Certified Architect, Foundations (CCAR-F) exam, design production agent systems, and learn agentic orchestration, tool and MCP design, Claude Code workflows, structured outputs, and context reliability with confidence.