How the exam works

The exam is criterion-referenced: you are measured against a fixed standard, not against other candidates. The passing score was set by a formal standard-setting study with subject matter experts, and scaled scoring equates across exam forms of differing difficulty — so 720 is not 72% of the items.

Your result is reported as pass/fail with the scaled score. The per-domain percentages on the score report are diagnostic only — the guide states they do not affect the pass/fail determination.

1. D1 Agentic Architecture & Orchestration 7 task statements 27%
2. D2 Tool Design & MCP Integration 5 task statements 18%
3. D3 Claude Code Configuration & Workflows 6 task statements 20%
4. D4 Prompt Engineering & Structured Output 6 task statements 20%
5. D5 Context Management & Reliability 6 task statements 15%

Every item is anchored to a production scenario. The guide publishes 6 of them and presents 4, picked at random, in any one sitting — so roughly 15 of the 60 items hang off each one. That is the reading load worth rehearsing: you stay inside a single system for a long run of questions rather than re-orienting on every item.

1. 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 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.

2. 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.

3. 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.

4. 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 Model Context Protocol (MCP) servers.

5. 5 Claude Code for Continuous Integration

   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.

6. 6 Structured Data Extraction

   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.

This is the section most preparation skips, and it is the one that saves the most time. The appendix lists 16 topics under one sentence: “The following related topics will not appear on the exam.” Reproduced verbatim:

• Fine-tuning Claude models or training custom models
• Claude API authentication, billing, or account management
• Detailed implementation of specific programming languages or frameworks (beyond what's needed for tool and schema configuration)
• Deploying or hosting MCP servers (infrastructure, networking, container orchestration)
• Claude's internal architecture, training process, or model weights
• Constitutional AI, RLHF, or safety training methodologies
• Embedding models or vector database implementation details
• Computer use (browser automation, desktop interaction)
• Vision/image analysis capabilities
• Streaming API implementation or server-sent events
• Rate limiting, quotas, or API pricing calculations
• OAuth, API key rotation, or authentication protocol details
• Specific cloud provider configurations (AWS, GCP, Azure)
• Performance benchmarking or model comparison metrics
• Prompt caching implementation details (beyond knowing it exists)
• Token counting algorithms or tokenization specifics

Read that list against your study plan. The recommended prep path works through the Claude API on one cloud platform after another — while the appendix above rules out “Specific cloud provider configurations (AWS, GCP, Azure)” by name, and the technologies it does list are the Agent SDK, MCP, Claude Code and the Claude API itself. Learning a provider's console is useful. It is not what this exam asks you.