Skilljar is a learning management system that hosts our educational content. You're logging into it to access the Anthropic course materials. This separate platform allows us to provide interactive learning experiences, track your progress, and ensure you have access to all course resources in an organized way.
Claude Certified Developer - Foundations Prep Course
Learn to build production-grade applications, agents, and workflows on Claude, and to make engineering decisions that determine whether code holds up when real users are depending on it.
Most developers start by using Claude in a chat window or sending a few API calls; that works until the code must survive production. A prompt that looked solid can fail on an untested input, a tool call can break halfway, a stream can get interrupted, an agent can run past its budget. The decisions of how you structure prompts, define tools, manage context, and wire agents, determine whether a working prototype can become a system you can defend in a heightened leadership review.
This course teaches the hands-on builder to operate Claude as a production system by building the engineering judgment that turns a prototype into something reliable, affordable, and controllable once deployed.
Learning objectives
By the end of this course, you'll be able to:
- Explain how Claude works at the level that affects engineering decisions: tokens, the context window as a fixed budget, sampling and non-determinism, model tiers, and SDK versus REST access patterns
- Write production-ready prompts using system prompts, XML, few-shot, and constraints, and diagnose why a prompt underperforms when first-pass results miss the mark
- Define and implement tool schemas, construct the tool-use loop, and manage extended thinking across multi-turn work
- Build a production agent with the right orchestration, memory scope, and human-in-the-loop checkpoints for irreversible actions
- Run Claude Code under a permission model, give it durable project context, package workflows as Skills and plugins, and connect Claude to enterprise systems through MCP without leaking credentials
- Build eval suites that define "done," create test and tracing layers that catch regressions, and keep a system inside its cost, latency, and reliability budget
- Secure an integration against prompt injection, untrusted input, and exposed secrets so a deployment survives a security or compliance review
- Package a working build into a reusable accelerator, choose where a workload runs across platforms, and contribute assets back into shared infrastructure
Prerequisites
Before starting this course, we recommend you complete: Claude 101, Claude Code 101, Claude Platform 101, Claude Code in Action, AI Fluency: Framework & Foundations, Building with the Claude API, Introduction to Model Context Protocol, Model Context Protocol: Advanced Topics, and AI Capabilities and Limitations.
Who this is for
The Claude Certified Developer Foundations course is for the hands-on builder who writes production code, builds agents, runs evals, and decides whether a customer's code makes it to production.
This course contains the following lessons:
MSO Foundations
Learn the model fundamentals and technical foundations the rest of the Developer Foundations course builds on.
57 Minutes
Production-Grade Prompting, Agents & Tool Use
Build your first production integration on Claude, with reliable prompts, tools, context management, and agent loops.
209 Minutes
Claude Code, MCP & Integration
Learn to make a working Claude integration configurable, shareable, and safe to connect to real systems.
142 Minutes
Production Engineering, Evals & Security
Learn to take an agent that works in development and prove it holds up under real production traffic.
211 Minutes
Accelerators & IP Contribution
Package a build that works into one that survives reuse, review, and deployment beyond the engagement that created it.
155 Minutes