AI Developer Certificate

Directory / Anthropic

Claude Certified Developer – Foundations

Anthropic's exam for engineers building on the Claude API, including tool use and agents.

What it signals

Practical assessment: Scenario-based multiple choice (2 of 4) Practical assessment
Scenario-based multiple choice. Proctored multiple-choice/multiple-response
Identity assurance: Proctored with identity verification (4 of 4) Identity assurance
Proctored with identity verification. Proctored via Pearson VUE (Pearson Professional Assessments): OnVUE online proctoring confirmed on Pearson page; test-centre delivery reported by third parties. Identity validated before exam. Closed book.
Depth: Associate (2 of 4) Depth
Associate. Associate level.
Experience expected: Under 6 months (1 of 4) Experience expected
Under 6 months. 6+ months hands-on LLM experience recommended
Portability: Mostly vendor-specific (1 of 4) Portability
Mostly vendor-specific. Claude-specific with some transferable LLM app concepts
Verifiability: Public badge or registry (4 of 4) Verifiability
Public badge or registry. Credly public badge

For hiring managers

  • Most developer-relevant Claude credential, but currently only obtainable by employees of Claude Partner Network organisations, so it signals partner/consultancy employment as much as skill. 12-month validity is short.

Verifying it

Digital badge issued through Credly by Pearson (publicly checkable badge URL).

What it covers

Published exam outline

  • Applications and Integration 33.1%
  • Model Selection and Optimization 16.8%
  • Agents and Workflows 14.7%
  • Prompt and Context Engineering 11%
  • Tools and MCPs 10.6%
  • Security and Safety 8.1%
  • Claude Code 3.1%
  • Evaluation, Testing and Debugging 2.6%

By topic

GenAI apps: Core focus (over 35%) (4 of 4) GenAI apps
Core focus (over 35%). >60% of blueprint is application integration, model selection and prompt/context engineering
Agents: Substantial (20 to 35%) (3 of 4) Agents
Substantial (20 to 35%). Agents and Workflows plus Tools and MCPs total about 25%
Classical ML: Not covered (0 of 4) Classical ML
Not covered. No model training content in blueprint
Operations: Touched on (under 10%) (1 of 4) Operations
Touched on (under 10%). Production concerns appear only inside other domains
Data: Not covered (0 of 4) Data
Not covered. No data engineering domain
Responsible AI: Touched on (under 10%) (1 of 4) Responsible AI
Touched on (under 10%). Security and Safety is 8.1%

Exam details

Who the provider says it is for. Engineers building with the Claude API, including tool use and agent development (Anthropic blog)

Format
Multiple-choice and multiple-response (third-party reports of official exam guide)
Delivery
Proctored via Pearson VUE (Pearson Professional Assessments): OnVUE online proctoring confirmed on Pearson page; test-centre delivery reported by third parties. Identity validated before exam. Closed book.
Code or hands-on work
No labs; multiple-choice only. Whether items contain code snippets to read is not verified.
Prerequisites
Registration is restricted to members of the Claude Partner Network (partner-organisation email); registration starts in Anthropic Partner Academy. Network membership is free for organisations.
Recommended experience
1-5 years engineering experience and 6+ months hands-on with Claude or comparable LLM systems; Python and/or TypeScript, REST APIs, CLI (third-party quoting exam guide)

Preparing

Not confirmed

These details were not available from an official source at the time of research.

  • Official exam guides sit behind Partner Academy login; domain weights, question counts, duration, pass score and 12-month validity are taken from third-party sites that state they quote the official guides
  • Renewal method
  • Test-centre availability (only OnVUE confirmed on Pearson page)
  • Whether exam items include code
Sources (6)