Urgent.News

What's breaking now, across thousands of outlets.

AI

Claude Certified Developer Foundations (CCDV-F): Exam Domains, Weights and Topics

This article summarises the Claude Certified Developer Foundations (CCDV-F) exam guide published by Anthropic: what the certification validates, the exam format, what the domain weights mean, and the topics listed under each domain. What CCDV-F validates Anthropic's exam guide states that the certification "validates that an individual can build, integrate, and ship production-grade applications,…

The Claude Certified Developer Foundations (CCDV-F) exam evaluates an individual's ability to build, integrate, and deploy production-grade applications, agents, and workflows using Anthropic's Claude platform at a foundational level. This certification is intended for technical professionals such as AI engineers, technical leads, and senior software engineers who possess one to five years of software engineering experience, six months of hands-on Claude experience, proficiency in Python and/or TypeScript, and fluency in REST APIs and CLI tools.

The exam consists of 53 multiple-choice and multiple-response questions to be completed in 120 minutes, delivered proctored online or at a testing center. A scaled score of 720 out of 1,000 is required to pass. The exam content is divided into eight domains, each assigned a weight indicating its relative importance in demonstrating competent performance. These domains are:

1. Applications and Integration (33.1%)

2. Model Selection and Optimization (16.8%)

3. Agents and Workflows (14.7%)

4. Prompt and Context Engineering (11.0%)

5. Tools and MCPs (10.6%)

6. Security and Safety (8.1%)

7. Claude Code (3.1%)

8. Eval, Testing, and Debugging (2.6%)

Within each domain, specific topics are listed, each with its own weight. For example, the Applications and Integration domain covers Claude Application Design (8.6%), Software Engineering Foundations (7.4%), Claude API Mechanics (6.8%), Configuration Management (4.1%), and Understanding Requirements (3.4%). The Model Selection and Optimization domain includes topics such as Technical Fundamentals (6.1%), LLM Fundamentals (5.2%), Cost and Token Management (2.8%), Model Selection and Tradeoffs (2.7%), and Agent Construction with Claude (5.3%).

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Bill Gates Says AI 'Kill Switch' Debate Shows How 'Nontechnical' People Are

His comments come as warnings from AI researchers, executives and whistleblowers have intensified, prompting calls for regulation.

  • Bill Gates dismisses AI kill switch idea as a distraction
  • Emphasizes mandatory monitoring and safeguards over shutdown mechanism
  • AI poses risks of cyberattacks, fraud, bioterrorism, and catastrophic harm

Can DeepSeek 4.1 Flash Replace Your $20 Coding Subscription?

A question came up at work recently: can we ditch our $20 monthly coding subscriptions and just use DeepSeek 4.1 Flash, paying per token instead?

  • DeepSeek 4.1 Flash outperformed Grok 4.5 in all Ship-Bench roles except Reviewer.
  • Model achieved 94.5 average score across five roles, excelling in Architect and UX Designer stages.
  • DeepSeek 4.1 Flash offers cost-effective pay-as-you-go pricing for limited usage.

A Certification That Changes Every Run Is a Coin Flip With a Signature

The plan was clean, and I believed every word of it: three real agents I had already built — a repo guardian, a release-notes drafter, an incident commander — would register in HivePlane , the control…

  • Certification results varied with each run, demonstrating nondeterminism.
  • Certification became repeatable with deterministic agents and controlled environment.
  • Field test revealed importance of writing evidence before verdict in stack.

More from Sunday 27 September →