The only training platform built for the Claude Certified Architect exam. Scenario-based, adaptive, and community-driven.
Passing score
The Certification
Design agentic loops, multi-agent coordinator patterns, subagent spawning, session management, and Agent SDK hooks.
Passing threshold
out of 1,000 scaled points
Tool Design & MCP Integration
Claude Code Config & Workflows
Exam format
4 picked at random per session
Prompt Engineering & Structured Output
Context Management & Reliability
How it works
Questions weighted by domain percentage. Harder questions when you're strong, fundamentals when you're weak.
Every question lives in a production scenario context — the same format as the actual Anthropic exam.
Track your 100–1000 estimated score in real time. Know your readiness before test day.
Practice UX
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?
Join AI builders preparing for the first Anthropic certification.