Claude Certified Developer - Foundations
Build, integrate, secure, test, and ship Claude applications, agents, workflows, tools, and MCP servers. Software engineers, AI engineers, and technical builders with Python or TypeScript experience and working knowledge of REST APIs and command-line tools. One to five years of software-engineering experience At least six months with Claude or comparable LLM systems Fluency with REST APIs, JSON, asynchronous code, and CLI tools Working knowledge of agents, context management, and MCP Agents and Workflows Choose workflows or agents from task constraints Design manager and subagent hierarchies Build with the Claude Agent SDK, custom loops, managed agents, and hooks Apply tool-loop, memory, context, and framework patterns Applications and Integration Translate business needs into functional and infrastructure requirements Apply system lifecycle practices Use messages, tools, streaming, vision, thinking, caching, batch, and third-party providers Apply REST, JSON, async, version-control, review, and refactoring practices Design instruction, schema, session, content-boundary, and plugin behavior Manage CLAUDE.md, settings, model, prompt, and plugin versions Claude Code Operate Rules, Skills, Commands, Agents, memory, sessions, headless mode, streaming mode, auto-mode, CLAUDE.md, initialization, and settings Eval, Testing, and Debugging Classify errors, select recovery, analyze traces, and isolate integration failures from model failures Model Selection and Optimization Explain tokens, sampling, context, non-determinism, thinking, effort, and prompting modes Integrate SDK and transport fundamentals Balance model quality, latency, cost, capability, and version changes Budget tokens…
Claude Certified Developer - Foundations: Build, integrate, secure, test, and ship Claude applications, agents, workflows, tools, and MCP servers.
This free community study path organizes 15 practical lessons in a deliberate order, then connects them to original diagnostics and practice. It does not issue a credential or reproduce protected exam questions.
Lessons in this path
- Study the Decisions, Not the Vocabulary
- Choose the Smallest Surface That Can Carry the Work
- Spend Capability Where Failure Is Expensive
- Turn a Request Into a Testable Contract
- Put Each Fact in the Right Kind of Context
- Validate the Claim, Not the Confidence
- The Messages API Is a State Machine
- Structured Output Is an Untrusted Contract
- A Tool Loop Is Controlled Delegation
- MCP Separates Capability From Host
- The Agent SDK Is a Harness, Not Permission
- Security Lives Outside the Prompt
3 more lessons continue in the interactive track.
Your progress
Domain weighting
Weights describe the official blueprint. Lesson coverage shows where this path trains each decision.
Lessons in order
Completion is stored only in this browser. Shared course lessons count everywhere they appear.
Go deeper
These existing course lessons add context and practice. They are optional and do not count toward required track progress.
Diagnostics and mocks
Practice results are percentages for this course, not official scaled exam scores.