Claude Certifications (Associate, Developer, Architect)
Anthropic's role-based credentials for people who work with Claude: Associate, Developer, Architect and Architect Professional. The developer and architect paths cover the API, tool use and agent systems.
Good to know: Anthropic says all of these certifications require membership of the Claude Partner Network. Firms join (membership is free) and register their practitioners, so an individual cannot sign up alone.
- Issuer
- Anthropic
- Level
- Specialty
- Exam format
- Proctored and identity-checked, delivered through Pearson
- Focus
- AI agents
- Who it is for
- Consultants, project leads, engineers and solution architects at firms in the Claude Partner Network.
- Before you start
- Every path starts at a foundation-level certification and advances to the professional level.
What the exam covers
Listed as the issuer lists them, with weights where the issuer publishes them.
- Claude Certified Associate: Foundations: everyday, practical use of Claude on projects
- Claude Certified Developer: Foundations: Claude API, tool use and agent development
- Claude Certified Architect: Foundations: designing and building agent systems
- Claude Certified Architect: Professional: integration architecture, governance and evaluation at enterprise scale
Key terms to know
Words from this certification's topic areas, in plain English. Know these and the study material will be much easier to follow.
- AI agent
- Software that uses a model to plan steps and use tools to reach a goal.
- Tool calling
- A model asking your code to run a function, such as a search or a database lookup.
- Model Context Protocol (MCP)
- A shared standard for connecting AI apps to tools and data.
- Prompt engineering
- Writing instructions so a model gives better answers.
- Context window
- How much text a model can consider at one time.
- Multi-agent system
- Several agents working together, each with its own role.
- Evaluation (evals)
- Tests that measure how good a model or an AI app is.
- Guardrails
- Rules and filters that block unsafe inputs or outputs.
- AI governance
- The policies, roles and records that control how AI is built and used in an organisation.
Build the knowledge here
Our lessons are not exam prep for this certification, but they cover the same ground.
Details last checked Oct 7, 2026 against the issuer's own pages. Exams, versions and rules change. Confirm on the official page before you book. We are not affiliated with Anthropic.