Claude Certified Architect — FoundationsBETA

Domina Claude. Certifícate como Claude Certified Architect de Anthropic.

La plataforma de preparación para el examen Claude Certified Architect de Anthropic. Preguntas basadas en escenarios reales, adaptativas al nivel que llevas.

Empezar gratisVer guía del examen
¿No sabes por dónde empezar?Descubre tu perfil en 3 preguntas →

Passing score

720 / 1000
100PASS →1000
27%Agentic ArchitectureMulti-Agent Systems18%Tool Design & MCP20%Claude Code Config20%Prompt Engineering15%Context ManagementAgent SDK HooksStructured OutputSubagent Spawning27%Agentic ArchitectureMulti-Agent Systems18%Tool Design & MCP20%Claude Code Config20%Prompt Engineering15%Context ManagementAgent SDK HooksStructured OutputSubagent Spawning
ScenarioCustomer Support AgentScenarioCode GenerationScenarioMulti-Agent ResearchDeveloper ProductivityScenarioCI/CD IntegrationScenarioData ExtractionMCP ServersHook SystemScore 720+ScenarioCustomer Support AgentScenarioCode GenerationScenarioMulti-Agent ResearchDeveloper ProductivityScenarioCI/CD IntegrationScenarioData ExtractionMCP ServersHook SystemScore 720+
0Exam Domains
0+Passing Score
0Scenarios
0%Free to Start

Claude Certified Architect – Foundations es la certificación oficial de Anthropic para profesionales que diseñan y despliegan sistemas basados en Claude AI. El examen evalúa cinco dominios: Agentic Architecture & Orchestration (27%), Tool Design & MCP Integration (18%), Claude Code Configuration & Workflows (20%), Prompt Engineering & Structured Output (20%) y Context Management & Reliability (15%). Presenta 4 de 6 escenarios al azar — Customer Support Agent, Code Generation, Multi-Agent Research, Developer Productivity, CI con Claude Code y Structured Data Extraction — con un score escalado de 100 a 1.000 puntos. El mínimo para aprobar es 720. claudepractice.com cubre los cinco dominios con preguntas adaptativas, módulos de concepto y simulacros completos para llegar al examen preparado.

The Certification

5 dominios.
Un examen.

01
27% of exam

Agentic Architecture
& Orchestration

Design agentic loops, multi-agent coordinator patterns, subagent spawning, session management, and Agent SDK hooks.

Agentic loopsMulti-agentSubagent spawningSession mgmtAgent SDK

Passing threshold

720

out of 1,000 scaled points

100PASS →1000
02
18%

Tool Design & MCP Integration

03
20%

Claude Code Config & Workflows

Exam format

6 Scenarios

4 picked at random per session

Customer Support Agent
Multi-Agent Research
Code Generation
CI/CD Integration
04
20%

Prompt Engineering & Structured Output

05
15%

Context Management & Reliability

How it works

Preparación distinta.

1
AI-Powered

Adaptive engine

Questions weighted by domain percentage. Harder questions when you're strong, fundamentals when you're weak.

Learn more
2
Exam-accurate

Scenario-first

Every question lives in a production scenario context — the same format as the actual Anthropic exam.

Learn more
3
Score tracking

Live score estimate

Track your 100–1000 estimated score in real time. Know your readiness before test day.

Learn more

Practice UX

Ve cómo funciona.

Practice Session · Domain 1 · Agentic ArchitectureQ 3 / 12

Scenario · Customer Support Agent

You're building a customer support agent with Claude. It must escalate to a human when confidence is low. Which orchestration pattern best describes this architecture?

AChain-of-thought prompting with tool use
BSupervisor-worker multi-agent pattern
CSingle agent with retry loop
DParallel agent fan-out

Get
certified.

Join AI builders preparing for the first Anthropic certification.