1
27% weight
Agentic Architecture & Orchestration
In scenarios: Customer Support Multi-Agent Research Developer Productivity
Content based on Anthropic's official Claude Certified Architect — Foundations Exam Guide.
Anthropic's official Skilljar practice exam — aim to consistently score above 900 here before you sit the real exam.
Open →15 questions per scenario, each mapped to the Skills-in bullet it tests with one-click links to study material.
Open →Symptom → answer patterns, escalation rules, Batches API quick-ref, and per-domain bullets. Printable.
Open →5-stage runbook from night-before prep to post-submit. Checkboxes persist locally.
Open →Start learning here — these five domains are the entire exam. Each card's % is its exam weight.
In scenarios: Customer Support Multi-Agent Research Developer Productivity
In scenarios: Customer Support Multi-Agent Research Developer Productivity
In scenarios: Code Generation Developer Productivity CI
In scenarios: CI Structured Data Extraction
In scenarios: Customer Support Code Generation Multi-Agent Research Structured Data Extraction
These are the exact six scenarios used on the exam — four appear per administration. Every question is framed inside one of them, so understanding each one pays off directly.
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 Model Context Protocol (MCP) tools (get_customer, lookup_order, process_refund, escalate_to_human). Your target is 80%+ first-contact resolution while knowing when to escalate.
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.
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.
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 Model Context Protocol (MCP) servers.
You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.
You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.