What is the Claude Certified Architect certification?

The Claude Certified Architect (CCA) certification, offered by Anthropic, validates expertise in designing, building, and deploying AI applications using Claude. The Foundations (CCA-F) level covers 5 official domains: Agentic Architecture, Claude Code, Prompt Engineering & Structured Output, Tools & MCP, and Context Management & Reliability.

How do I prepare for the CCA-F exam?

This free study platform offers 116 lessons across the 5 official exam domains, 800+ practice questions, unlimited weighted mock exams, and spaced-repetition flashcards to prepare for the CCA-F exam. It features interactive quizzes, diagnostics, and progress tracking.

What are the 5 official CCA-F exam domains?

The CCA-F exam covers 5 official domains weighted as follows: Agentic Architecture & Orchestration (27%), Claude Code Configuration & Workflows (20%), Prompt Engineering & Structured Output (20%), Tool Design & MCP Integration (18%), and Context Management & Reliability (15%). A solid background in Claude fundamentals is assumed.

How many questions are on the CCA-F exam?

The CCAR-F (Claude Certified Architect - Foundations, formerly CCA-F) exam has 60 items in 120 minutes, mixing multiple-choice and multiple-response questions. It is scored on a 1000-point scale with 720 required to pass. It is proctored (online via Pearson OnVUE or at a Pearson test center), closed-book, and valid for 12 months, renewed via a free non-proctored assessment on the Anthropic Partner Academy.

How long does the CCA-F exam take?

The CCA-F exam allows 120 minutes (2 hours) to complete 60 questions. Candidates average roughly 2 minutes per question. Good time management means reading each scenario carefully and flagging uncertain answers for review rather than lingering.

What is the passing score for the CCA exam?

The CCA-F exam requires a passing score of 720 out of 1000 points. The exam mixes multiple-choice and multiple-response items, is closed-book and proctored (Pearson OnVUE online or a Pearson test center). It is designed to be difficult, only well-prepared candidates should expect to pass.

Is the Claude Certified Architect certification worth it?

The Claude Certified Architect certification demonstrates verified expertise in building AI applications with Claude. As organizations increasingly adopt AI agents and Claude-powered workflows, certified architects are positioned to lead architecture decisions, optimize production deployments, and implement best practices across multi-agent systems.

Claude Code is a CLI tool developed by Anthropic that brings Claude's coding capabilities directly into the development environment. It supports edit mode and plan mode, keyboard shortcuts, slash commands, and a skills directory. Claude Code accounts for approximately 20% of the CCA-F exam content.

How do Claude agents work?

Claude agents operate using an agentic loop: send a request to the Messages API, process Claude's response, execute any tool calls Claude requests, append the results, and repeat. The stop_reason field signals when the task is done. Agentic architecture accounts for approximately 27% of the CCA-F exam.

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open standard developed by Anthropic and governed by the Linux Foundation's Agentic AI Foundation. It provides a three-layer architecture (Host, Client, Server) with three primitives: Resources (application-controlled), Tools (model-controlled), and Prompts (user-controlled), built on JSON-RPC 2.0.

What domains are tested on the CCA exam?

The CCA-F exam tests 5 official domains weighted as follows: Agentic Architecture & Orchestration (27%), Claude Code (20%), Prompt Engineering & Structured Output (20%), Tools & MCP (18%), and Context Management & Reliability (15%).

Can I take the CCA practice exam for free?

Yes. This platform provides unlimited free mock exams (60 questions, 120 minutes, weighted to the official domain split), domain-specific practice, and flashcards. No registration or payment is required.

How do I get started with Claude AI development?

Start with the Fundamentals: learn what Claude is, understand the Messages API, manage tokens, write system prompts, and configure sampling parameters. Claude offers three model tiers: Sonnet (general-purpose), Opus (complex reasoning), and Haiku (fast and cost-effective for simple tasks).

What is the Claude Certified Architect certification?

The Claude Certified Architect (CCA) certification, offered by Anthropic, validates expertise in designing, building, and deploying AI applications using Claude. The Foundations (CCA-F) level covers 5 official domains: Agentic Architecture, Claude Code, Prompt Engineering & Structured Output, Tools & MCP, and Context Management & Reliability.

How do I prepare for the CCA-F exam?

This free study platform offers 116 lessons across the 5 official exam domains, 800+ practice questions, unlimited weighted mock exams, and spaced-repetition flashcards. All content is free and open-source.

What are the 5 official CCA-F exam domains?

The exam covers 5 official domains weighted as follows: Agentic Architecture & Orchestration (27%), Claude Code Configuration & Workflows (20%), Prompt Engineering & Structured Output (20%), Tool Design & MCP Integration (18%), and Context Management & Reliability (15%).

How many questions are on the CCA-F exam?

The CCAR-F (formerly CCA-F) exam has 60 items mixing multiple-choice and multiple-response questions with a 120-minute time limit. The passing score is 720 out of 1000. The exam is proctored (Pearson OnVUE online or a Pearson test center) and closed-book.

Is the CCA-F exam free?

The study platform is completely free and open-source. The CCA-F certification exam itself is administered by Anthropic and requires payment. This platform provides all the preparation materials you need at no cost.

How long does it take to get Claude Certified Architect certified?

Most learners complete the 116 lessons and pass the certification in 4 to 8 weeks with consistent study. The platform tracks your progress across all 5 domains with spaced repetition and learning analytics to optimize your study time.

What is the passing score for the CCA-F exam?

The passing score for the CCAR-F (Claude Certified Architect - Foundations) exam is 720 out of 1000 possible points. The exam has 60 items mixing multiple-choice and multiple-response questions and a 120-minute time limit. Credentials are valid 12 months with free non-proctored renewal on the Partner Academy.

What is Model Context Protocol (MCP)?

Model Context Protocol (MCP) is an open protocol developed by Anthropic that standardizes how AI applications connect to external systems. It uses a three-layer architecture (Host, Client, Server) with three primitives: Resources, Tools, and Prompts.

How do practice exams help with the CCA-F certification?

Practice exams simulate the real CCA-F testing experience with unlimited mocks weighted to the official 27/20/20/18/15 split, 60 questions, 120 minutes, and 720/1000 scoring. Each exam includes detailed explanations and performance analytics.

What is Claude Code and how is it used?

Claude Code is a CLI tool that brings Claude's coding capabilities directly into your terminal with file system access, command execution, and project context. It features edit mode for making changes and plan mode for safe exploration and analysis.

What is the Agents SDK in Claude?

The Claude Agents SDK is a framework for building stateful, long-running AI agents. It provides agent lifecycle management, state persistence, tool binding, inter-agent communication, and observability.

What are the three Claude model tiers?

Claude offers three model tiers: Sonnet for general-purpose tasks (fast, high intelligence, moderate cost), Opus for complex reasoning (highest intelligence, slower, adaptive thinking), and Haiku for simple high-throughput tasks (fastest, lowest cost). All share the same Messages API.

All Lessons

Following a prompt update, Helpdesk Copilot overall accuracy rises from 82% to 86%, but restricted account safety violations jump from 0% to 12%. Why did relying on the aggregate accuracy metric fail as a release signal?

AAggregate metrics average all cases together, allowing high volume on routine tickets to mask critical failures in high-risk slices.BMathematical averages are uncalibrated when evaluating sample sizes greater than 50 tickets.CEvaluation harnesses automatically round percentage scores down when safety violations occur.DAccuracy metrics only measure retrieval latency rather than generated text correctness.

1 / 1

advanced 45 min

Day 18: Measure Quality and Diagnose Failures

Measure Quality and Diagnose Failures

Based on Anthropic Claude documentation and the CCA-F exam blueprint. Updated August 2026.

Loading lesson content...

Review the evaluation failure triage function below. What is the primary engineering benefit of categorizing errors with this step-by-step taxonomy rather than labeling them generically as 'model errors'?

AIt allows the system to automatically bill the model provider for failed inference calls.BIt ensures that subsequent evaluation runs will complete with zero test failures.CIt eliminates the need to maintain human-in-the-loop review workflows in production.DIt pinpoints the exact pipeline stage responsible, directing fixes to retrieval, prompt instructions, or policy gates.

1 / 1

When establishing release criteria for Helpdesk Copilot, how should the team treat zero-tolerance safety metrics (e.g., unauthorized access promises) compared to soft metrics (e.g., draft conciseness)?

ASoft metrics and safety metrics should be averaged together into a single composite quality score.BSafety metrics must act as non-negotiable hard gates where any single violation blocks release, regardless of soft metric gains.CSoft metrics take precedence because end-user satisfaction depends primarily on concise response phrasing.DSafety violations are acceptable in production if the overall retrieval latency remains under 400ms.

1 / 1

Warm-UpQuick check before we dive in

Day 18: Measure Quality and Diagnose Failures

On this page

Check Your UnderstandingTest your knowledge so far

Lesson ReviewSolidify what you've learned