Claude Certified Architect - Foundations
255 practice questions
Last reviewed: April 2026
Written from scratch against the official Anthropic exam guide
Personal notes and resource links for your study journey
Track your exams, notes, and resources day by day
The Claude Certified Architect - Foundations (CCA-F) is the first AI-company-specific architect certification, launched by Anthropic in March 2026. It validates the ability to design, build, and operate production systems on the Claude platform - spanning the Claude API, Claude Code, and the Model Context Protocol (MCP). The exam targets AI engineers, solutions architects, and developers who build agentic workflows, integrate external tools through MCP servers, and ship reliable Claude-powered applications. At 60 multiple-choice questions in 120 minutes with a 720/1000 passing score and a $99 fee, it sits at a foundational level but demands hands-on familiarity with prompt engineering, tool design, context management, and orchestration patterns unique to the Claude ecosystem.
The heaviest domain at 27%. Covers multi-step agent design, orchestration patterns (sequential, parallel, router), handoff protocols between sub-agents, human-in-the-loop checkpoints, and failure-recovery strategies. Expect questions on when to use a single-agent loop versus a multi-agent graph and how to manage shared state across agent steps.
Weighted at 20%. Tests knowledge of Claude Code setup - CLAUDE.md conventions, permission models, hook configuration, slash commands, MCP server integration within Claude Code, and CI/CD workflows that leverage Claude Code for automated coding tasks. Candidates who have only used the API without Claude Code will find this domain challenging.
Also 20%. Covers system-prompt design, prefilling, chain-of-thought elicitation, extended thinking, structured JSON/XML output via tool_use and constrained generation, and techniques for reducing hallucination. Goes beyond basic prompting into production-grade patterns - prompt versioning, A/B testing, and evaluation frameworks.
Weighted at 18%. Focuses on designing tool schemas, MCP server implementation (resources, tools, prompts, sampling), transport layers (stdio, SSE, Streamable HTTP), security boundaries for tool execution, and best practices for tool descriptions that minimize misuse. Expect scenario-based questions on debugging tool-call failures and handling partial tool results.
The lightest domain at 15%, but critical for production systems. Covers context-window budgeting, summarization strategies, caching (prompt caching, ephemeral caching), retrieval-augmented generation patterns, rate-limit handling, retry/backoff logic, and monitoring/observability for Claude API calls. Questions often pair context-window math with cost-optimization trade-offs.
$130k-$185k-$280k USD annual
Range covers US-based AI engineering and solutions-architect roles where Claude API or LLM integration is a primary skill. Entry-level and non-coastal positions trend toward the low end; senior AI architects at frontier-AI companies and well-funded startups push well above the high end ($300k-$450k+ TC). The certification is new and does not yet carry the hiring weight of established cloud certs - its value is strongest as a signal of hands-on Claude platform expertise paired with a portfolio of shipped AI applications.
Source: levels.fyi 2025-2026 AI/ML engineering data, Glassdoor 2025-2026, LinkedIn salary insights for Claude/LLM-related roles. Figures are approximate; actual compensation depends on role, region, and experience.
Demand for engineers who can build production-grade LLM applications has surged since 2024, with "Claude API," "MCP," and "agentic workflows" appearing in a rapidly growing share of AI-engineering job postings. As the first vendor-issued certification for Claude-specific skills, CCA-F occupies a unique niche: it lets candidates demonstrate familiarity with the Claude ecosystem - prompt engineering, tool use, Claude Code, and MCP - in a way no generic AI cert covers. Early adoption is strongest among AI consultancies, startups building on the Anthropic stack, and enterprise teams standardizing on Claude for internal tooling. The certification is most valuable when paired with demonstrable project work (open-source MCP servers, shipped Claude-powered products); on its own it signals foundational competence rather than deep expertise.
There are no formal prerequisites. Anthropic recommends at least three months of hands-on experience building with the Claude API, including practical exposure to tool use, structured output, and at least one agentic workflow that went beyond a single prompt-response cycle.
Familiarity with the Model Context Protocol (MCP) and Claude Code is strongly recommended. Several questions assume you can reason about MCP server architecture (resources, tools, prompts, transport layers) and Claude Code configuration (CLAUDE.md, hooks, permissions). Candidates who have only used Claude through the chat interface without API or CLI experience will find the exam significantly harder than the "foundations" label suggests.
CCA-F is positioned as a foundational certification but should not be mistaken for an easy introductory exam. The 60-question, 120-minute format gives a comfortable two minutes per question, and all questions are multiple-choice - there are no labs or performance-based tasks. However, questions frequently present realistic architectural scenarios that require combining knowledge across domains: for example, choosing an orchestration pattern while also considering context-window limits and tool-call reliability.
Common stumbling blocks include the Claude Code domain (unfamiliar to API-only users), context-window budget calculations with prompt caching, MCP transport-layer trade-offs, and questions that test the boundary between Claude API features and general LLM concepts. Plan on 15-25 hours of study if you actively build with Claude daily, 40+ hours otherwise. The $99 fee and online proctoring make retakes relatively painless.
Inaugural version. 60 MCQ, 120 minutes, 720/1000 pass, $99 USD, online-proctored. Covers Claude API (including extended thinking and tool use), Claude Code, MCP, agentic orchestration, prompt engineering, and context management. Two-year validity.
It's Anthropic's foundational certification for building on Claude - the first AI-company-specific architect credential, launched in 2026. It validates designing, building, and operating production systems across the Claude API, Claude Code, and the Model Context Protocol (MCP), including agentic workflows, tool design, prompt engineering, and context management. The exam is 60 multiple-choice questions in 120 minutes with a 720/1000 passing score. See the CCA-F hub for the full domain breakdown.
It's open to everyone - it's a public, foundational certification with a standard exam fee, not a partner-only or invite-only program. Anyone building with Claude (developers, AI engineers, solutions architects) can register and take it; you don't need to be an Anthropic partner or customer of a particular tier.
It's positioned as foundational, but "foundational" here still means hands-on familiarity with the Claude ecosystem - you're expected to understand agentic orchestration, Claude Code configuration, MCP tool integration, and prompt/structured-output patterns, not just Claude trivia. People who've only used the API casually tend to find the Claude Code and MCP domains challenging. Drilling practice questions is the best way to gauge readiness.
60 multiple-choice questions in 120 minutes, with a passing score of 720 out of 1000. That's a comfortable two minutes per question, and there's no penalty for wrong answers, so answer every one.
It's not free - the exam costs $99 USD. Anthropic provides free study material (documentation and guidance), but the exam itself is paid. See our Anthropic exam info page for registration details.
You register through Anthropic's certification portal and take the exam online. Part of the enrollment involves an access step (agreeing to the exam's terms and confirming your details) before you can sit it. Our Anthropic exam info page walks through the registration process and requirements.
That's part of Anthropic's enrollment flow - before taking the exam you complete an access/attestation step, confirming your identity and agreeing to the certification's terms and conduct policy. It's a standard gating step in the registration process, not a separate approval or partner requirement, and it's how Anthropic grants you access to sit the exam.
Get genuinely hands-on with the Claude ecosystem - build agentic workflows with the API, use Claude Code (CLAUDE.md, permissions, hooks, slash commands), and wire up MCP servers - then reinforce with the exam's core themes (prompt engineering, structured output, context management, orchestration). Our CCA-F question bank covers every domain with explanations, the Playbook distills the architecture patterns, and the hands-on lab reinforces real Claude workflows.
Yes, if you build AI applications with Claude or want to signal that skill - it's the first architect certification tied to a specific AI provider, it's timely as agentic and MCP-based systems take off, and it validates practical, in-demand skills. As a foundational cert it's a strong differentiator now precisely because it's new. See how it fits among AI certs on our State of Certifications report.
It's aimed at AI engineers, solutions architects, and developers who build on Claude - people designing agentic workflows, integrating external tools through MCP servers, and shipping production Claude-powered applications. It suits anyone moving from casual API use to building reliable, well-architected Claude systems.
The exam itself is 120 minutes, and total prep time depends on your Claude experience - developers already building with the API, Claude Code, and MCP can often be ready in a few weeks, while those newer to the ecosystem should budget more time to get hands-on first. The fastest path is building real Claude projects alongside working through practice questions.
CCA-F (Claude Certified Architect - Foundations) is a considered an entry-level exam testing breadth of conceptual understanding rather than hands-on depth Foundational-level exam. Most candidates need 30-80 hours of study spread over 3-6 weeks for foundational-level exams. Most candidates who score consistently above the passing threshold on practice exams pass on their first attempt.
Most candidates need 30-80 hours of study spread over 3-6 weeks for foundational-level exams. Time-to-pass varies widely by prior experience. Engineers with hands-on production experience in the underlying technology typically need less; candidates new to the platform should plan toward the upper end of that range.
Yes - for cloud engineers, architects, and consultants who work with Anthropic, CCA-F is generally worth it. It is a recognized credential that signals validated knowledge to employers, recruiters, and clients; whether the time and fee pay off for you depends on your role and goals.
The passing score for CCA-F is 720 / 1000. The exam contains 60 questions and lasts 2 hr.
The CCA-F exam fee is $99 USD. Fees are set by Anthropic and may vary by region; always confirm the current price on the official Anthropic certification page before booking.
Anthropic has not yet published an explicit validity period for the CCA-F certification. The program launched in March 2026; renewal policies are expected to be announced as it matures.
Yes, Anthropic certifications are delivered online only - there are no in-person test centers. The exam runs in a secure proctored browser; you'll need a quiet private room, webcam, microphone, stable broadband, and a government photo ID.
The CCA-F exam-simulation mode on CertLabPro mirrors the real exam: 60 questions in 2 hr, with the same 720 / 1000 passing threshold. You also get 15 study modes in total, and Browse mode renders every question with its answer and explanation statically.
$130k-$280k USD is the typical US salary range for roles that value CCA-F, per levels.fyi 2025-2026 AI/ML engineering data, Glassdoor 2025-2026, LinkedIn salary insights for Claude/LLM-related roles. Actual pay depends on seniority, location, and role - senior and architect positions trend higher, entry-level lower.
Yes - a focused month is realistic for most candidates. Most candidates need 30-80 hours of study spread over 3-6 weeks for foundational-level exams. If the Anthropic platform is new to you, give yourself more time; with hands-on experience you may need less.
Not really - CCA-F is an entry-level exam that assumes no prior hands-on experience, which makes it a common first certification.