클로드 인증 건축가가 되세요

[  ](https://anthropic.com) ## Header Navigation [ Anthropic Academy ](https://www.anthropic.com/learn) [ Courses ](https://anthropic.skilljar.com/) [ Sign In ](https://anthropic.skilljar.com/auth/login?next=%2Fclaude-certified-architect-foundations-access-request) [ Anthropic Academy ](https://www.anthropic.com/learn) [ Courses ](https://anthropic.skilljar.com/) [ Sign In ](https://anthropic.skilljar.com/auth/login?next=%2Fclaude-certified-architect-foundations-access-request) # Become a Claude Certified Architect Prove your expertise in building production-grade applications with Claude. [Register for the Exam](https://anthropic.skilljar.com/checkout/335ekdcl2m147)[Download the exam guide↓](https://everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F8lsy243ftffjjy1cx9lm3o2bw%2Fpublic%2F1773274827%2FClaude+Certified+Architect+%E2%80%93+Foundations+Certification+Exam+Guide.pdf) Not an Anthropic partner? [Apply to become one →](https://claude.com/partners)  Exclusive for Anthropic Partners A ~301 level exam for practitioners at partner companies with foundational knowledge who are ready to demonstrate deeper, applied expertise.  120 min Proctored Exam Complete 60 multiple-choice questions end-to-end in a single session. No external resources or breaks.  Your Score Report Results within 2 business days with detailed section breakdowns. Digital certificate recognized by companies using Claude.  Free for Early Access Free for the first 5,000 partner company employees. General availability will be $99.  ## What You’ll Be Tested On 60 questions across five core competency areas ● Agentic Architecture & Orchestration27% Design agentic loops, orchestrate multi-agent systems with coordinator-subagent patterns, implement task decomposition, and manage session state and workflow enforcement. ● Tool Design & MCP Integration18% Design effective tool interfaces with clear boundaries, implement structured error responses, integrate MCP servers, and distribute tools appropriately across agents. ● Claude Code Configuration & Workflows20% Configure CLAUDE.md hierarchies, create custom slash commands, apply path-specific rules, know when to use plan mode, and integrate into CI/CD pipelines. ● Prompt Engineering & Structured Output20% Design prompts with explicit criteria, apply few-shot techniques, enforce structured output with JSON schemas, and implement validation and retry loops. ● Context Management & Reliability15% Preserve critical information across long interactions, design escalation patterns, manage error propagation in multi-agent systems, and handle uncertainty with confidence calibration. ## Exam Scenarios Each exam draws 4 scenarios at random from this set of 6. Every scenario frames a realistic production context for a set of questions. 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 MCP tools (get_customer, lookup_order, process_refund, escalate_to_human). Your target is 80%+ first-contact resolution while knowing when to escalate. Agentic Architecture & OrchestrationTool Design & MCP IntegrationContext 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. Claude Code Configuration & WorkflowsContext 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. Agentic Architecture & OrchestrationTool Design & MCP IntegrationContext 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 MCP server