overview

Validates that you can build, integrate and ship Claude-powered applications, agents and workflows. It covers API integration, agent and tool construction, Claude Code, prompt and context engineering, evals and debugging, security, and model selection for cost and latency. Application and integration work carries a third of the exam.

Who it's for. Software, AI and ML engineers and technical leads who build on Claude. Typically they have one to five years in software engineering, six months or more with Claude or similar LLM systems, and work in Python or TypeScript.

Exam code
CCDV-F
Questions
53, multiple choice and multiple response
Time
120 minutes
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

Start now with the live hub: Architect Foundations.

domain map

DomainWeight
Agents and workflows 14.7%
Applications and integration 33.1%
Claude Code 3.1%
Eval, testing and debugging 2.6%
Model selection and optimization 16.8%
Prompt and context engineering 11.0%
Security and safety 8.1%
Tools and MCPs 10.6%

Domains and weights from Anthropic's official exam guide.