Study free. Pay only for what you need.

The **Claude Certified Architect – Foundations** certification (exam code **CCAR-F**) validates that practitioners can make sound architectural and configuration decisions when building production-grade applications with Claude. The exam tests practical judgment — not just conceptual recall — across five weighted domains: - **Agentic Architecture & Orchestration** (27%) — agentic loops, coordinator-subagent patterns, parallel subagent execution, hooks, and session management - **Claude Code Configuration & Workflows** (20%) — CLAUDE.md hierarchy, `.claude/rules/` path-scoped rules, custom slash commands and skills, plan mode vs. direct execution, and CI/CD integration - **Prompt Engineering & Structured Output** (20%) — few-shot prompting, explicit review criteria, `tool_use` with JSON schemas, batch processing with the **Message Batches API**, and multi-pass review architectures - **Tool Design & MCP Integration** (18%) — writing effective tool descriptions, structured error responses, tool distribution across agents, and MCP server configuration - **Context Management & Reliability** (15%) — context window optimization, escalation patterns, error propagation, provenance tracking, and human review workflows Questions are grounded in realistic scenarios — building a **customer support resolution agent**, designing a **multi-agent research pipeline**, integrating **Claude Code into CI/CD**, and extracting **structured data from unstructured documents** — drawn from a bank of six, with four presented per exam sitting. The exam consists of **60 items** (multiple-choice and multiple-response) delivered in **120 minutes** via **Pearson VUE** (online proctored or test center). The passing score is a **scaled score of 720** on a 100–1,000 scale, and the credential is valid for **12 months**. The ideal candidate has **6+ months of hands-on experience** building with the **Claude API**, **Claude Agent SDK**, **Claude Code**, and **Model Context Protocol (MCP)**, with practical familiarity with both capabilities and production limitations of large language models.

The **Claude Certified Architect – Professional** (exam code **CCAR-P**) validates that a practitioner can design, build, and deliver production-grade AI solutions on **Anthropic's Claude platform** — from model selection and prompt engineering through enterprise integration, governance, and stakeholder communication. It is intended for **mid- to senior-level professionals** such as solution architects, AI/ML engineers, technical leads, and senior software engineers who translate complex business requirements into scalable, secure, and reliable Claude-powered systems. There are **no mandatory prerequisites** — the credential is awarded based on exam performance alone. Anthropic recommends at least **3+ years of systems architecture or platform engineering experience** and **6+ months of hands-on Claude or comparable LLM experience in production**. The exam consists of **63 multiple-choice and multiple-response items** completed in **120 minutes**, delivered via online proctoring or a Pearson VUE test center. The **passing score is 720** on a scaled range of 100–1,000. The credential is valid for **12 months** and can be renewed through a free, non-proctored assessment on the Anthropic Partner Academy before it lapses.

The **Claude Certified Associate – Foundations** credential (exam code **CCAO-F**) validates your ability to apply **Claude** effectively in real-world business workflows — moving beyond basic Q&A to process redesign, task automation, and structured project development. It's designed for professionals in roles such as operations, marketing, project management, education, and communications who use Claude as a core productivity tool, not for software developers or API specialists. The exam covers seven **content domains**: - **Prompting and Task Execution** — crafting and iterating effective prompts - **Output Evaluation and Validation** — identifying hallucinations, applying fact-checking, selecting output formats - **Product and Model Selection** — choosing between Haiku, Sonnet, and Opus; managing context limits - **Workflow Integration and Solution Design** — embedding Claude into existing processes - **Configuration and Knowledge Management** — setting up Projects, instructions, and knowledge connectors - **Governance, Risk, and Responsible Use** — data sensitivity, privacy, and organizational AI policy - **Troubleshooting and Optimization** — diagnosing and improving underperforming prompts No mandatory prerequisites or coding experience is required. The exam consists of **60 multiple-choice and multiple-response items** in **120 minutes**, with a passing **scaled score of 720** (on a 100–1,000 scale). The credential is valid for **12 months** and can be renewed through a free assessment on the Anthropic Partner Academy.

The **Claude Certified Developer – Foundations** (exam code **CCDV-F**) certifies that you can build, integrate, and ship production-grade applications, agents, and workflows on Anthropic's **Claude** platform. The exam covers eight content domains, weighted by importance: - **Applications and Integration** (33.1%) — API mechanics, SDK usage, streaming, application design, and configuration management - **Model Selection and Optimization** (16.8%) — LLM fundamentals, model tiers (Opus/Sonnet/Haiku), token budgeting, and caching - **Agents and Workflows** (14.7%) — agent architecture, the Claude Agent SDK, custom agent loops, and agentic frameworks - **Prompt and Context Engineering** (11.0%) — prompt writing, context-window management, output validation - **Tools and MCPs** (10.6%) — function calling, MCP server development, and tool-type tradeoffs - **Security and Safety** (8.1%) — prompt injection defense, guardrails, hooks, and secrets management - **Claude Code** (3.1%) — Skills, Commands, CLAUDE.md, and settings.json - **Eval, Testing, and Debugging** (2.6%) — trace analysis, error handling, and structured-output validation Recommended experience includes **1–5 years of software engineering**, at least **six months of hands-on work with Claude or a comparable LLM**, proficiency in **Python and/or TypeScript**, and fluency with **REST APIs** and CLI tools. There are no mandatory prerequisites — the credential is awarded on exam performance alone. The exam consists of **53 multiple-choice and multiple-response items**, has a **120-minute time limit**, and requires a **scaled score of 720** (on a 100–1,000 scale) to pass. It is delivered via **Pearson VUE**, either online-proctored or at a test center, and the credential is valid for **12 months**.