# The Six Exam Scenarios Let's examine each scenario in detail so you know what to expect. ## Scenario 1: Customer Support Agent This scenario tests your ability to design **agentic loops with safety constraints**. Expect questions about: - Prerequisite gates (verify before refund) - Escalation triggers (ambiguous identity, angry customer) - Structured handoff to human agents - Workflow enforcement via hooks vs. prompts ## Scenario 2: Code Generation Pipeline Tests **tool design and structured output**: - Tool interface design for code operations - Error categorization (syntax vs. semantic vs. runtime) - Multi-pass review (generate, then independently review) - Structured error responses with actionable feedback ## Scenario 3: Multi-Agent Research System Tests **orchestration and context passing**: - Hub-and-spoke architecture - Subagent isolation (no shared memory) - Explicit context passing with structured metadata - Iterative refinement loops ## Scenario 4: Developer Productivity Tool Tests **Claude Code configuration**: - CLAUDE.md hierarchy (user/project/directory) - Custom commands and skills - Plan mode vs. direct execution - Path-specific rules for different services ## Scenario 5: CI/CD Quality Pipeline Tests **automation and prompt engineering**: - Non-interactive mode (`-p` flag, `--output-format json`) - Session context isolation - Explicit review criteria - Batch processing patterns ## Scenario 6: Structured Data Extraction Tests **reliability and context management**: - Schema design with nullable fields - Confidence scoring and provenance tracking - Error propagation vs. silent suppression - Batch processing with the Message Batches API When you see a scenario on the exam, immediately identify which domain it primarily maps to. This helps you recall the right mental models.

Claude Certified Architect — Foundations

Chapters

The CCA Exam: Format, Strategy & Roadmap

The Agentic Loop

Multi-Agent Orchestration

Subagent Invocation & Context Passing

Workflow Enforcement & Handoff

Agent SDK Hooks

Task Decomposition & Session Management

Tool Interface Design

Structured Error Responses

Tool Distribution & tool_choice

MCP Server Integration & Built-in Tools

CLAUDE.md Configuration Hierarchy

Custom Commands, Skills & Path Rules

Plan Mode, Refinement & CI/CD

Explicit Criteria & Precision

Few-Shot Prompting

Structured Output with tool_use

Validation, Retry & Batch Processing

Multi-Pass Review Architectures

Context Preservation & Escalation

Error Propagation, Exploration & Provenance

Full Practice Exam