overview

Tests whether you can make sound trade-off decisions when building real solutions with Claude Code, the Claude Agent SDK, the Claude API and MCP. Every question sits inside a production scenario, such as a customer support agent, a multi-agent research pipeline, Claude Code in CI/CD, developer tooling or structured data extraction. It rewards practical judgement about architecture and configuration, not recall.

Who it's for. Solution architects who design and ship production applications with Claude, typically with six months or more hands-on with the Claude API, the Agent SDK, Claude Code and MCP.

Exam code
CCAR-F
Questions
60, multiple choice and multiple response
Time
120 minutes
Structure
Scenario-based, with 4 scenarios drawn at random from a bank of 6
Passing score
720 on a 100–1,000 scale
Fee
$125 USD
Valid for
12 months
Delivery
Proctored, online or at a Pearson VUE test centre

where it sits

domain map

DomainWeight
Agentic architecture and orchestration 27%
Tool design and MCP integration 18%
Claude Code configuration and workflows 20%
Prompt engineering and structured output 20%
Context management and reliability 15%

Domains and weights from Anthropic's official exam guide.

study guides

Study guides are in preparation.

practice questions

Practice questions are in preparation.

resources