Software development
Artificial Intelligence
Cloud
View all courses
Learn
Connect
Blog
Resource hub
Featured resource
2025 Tech Upskilling Playbook
Tech Upskilling Playbook

Build future-ready tech teams and hit key business milestones with seven proven plays from industry leaders.

Check it out

Build AI Agents with Claude Agent SDK

Course Summary

This course is designed to transition developers from building simple chatbots to engineering autonomous systems that can navigate filesystems, execute shell commands, and manage complex infrastructure. Participants will move beyond prompt engineering into agent architecture, learning to use Claude as a reasoning engine that drives external tools. The course covers the Model Context Protocol (MCP) for tool discovery, the creation of persistent Skills, and the orchestration of Subagents to solve multi-domain problems like VPC provisioning and automated DevOps.

Prerequisites:

In order to succeed in this course, you will need:

  • Proficiency in Python
  • Familiarity with AWS services (EC2, VPC, IAM) and Command Line Interfaces (CLI)
  • Foundational LLM Knowledge
Purpose
Transition from building simple chatbots to engineering autonomous systems
Audience
Senior Engineers looking to build autonomous systems with Claude Agent SDK
Role
AI Engineers & LLM Developers | DevOps & Platform Engineers | Software Architects | Technical Product Leads
Skill level
Intermediate
Style
Lecture | Hands-on Activities | Labs
Duration
3 days
Related technologies
Gen AI | Python | AWS | Claude Code | Terraform | YAML

 

Learning objectives
  • Implement the Agent Loop cycle using the ClaudeSDKClient
  • Use the SDK tools to automate code refactoring and auditing
  • Build Reusable Skills
  • Integrate the Bash tool to execute AWS CLI, Terraform, and CloudFormation commands
  • Orchestrate Subagents
  • Connect to external tool providers using the Model Context Protocol
  • Implement Safety Guardrails

What you'll learn:

In this Build AI Agents with Claude Agent SDK course, you'll learn:

The Agentic Loop & SDK Fundamentals

  • Think-Act-Observe loop
  • SDK setup
    • ClaudeSDKClient
    • ClaudeAgentOptions

Claude Filesystem and Shell

  • Discovery Tools for matching, ingestion, and searching
    • Glob, Grep, Edit
  • Mutation Tools for file manipulation
    • Edit, MultiEdit, Write
  • The Bash Tool for executing shell commands for AWS/Terraform

Context & Multi-Turn Persistence

  • Multi-turn conversations
  • ClaudeSDKClient persistence
  • Context Window Management for developing complex artifacts
  • Permission Modes

Skills as Artifacts

  • Creating .claude/skills/ artifacts
  • Skill Architecture - writing SKILL.md files with YAML
  • Orchestration - loading and invoking specialized skills

Subagents & Task Delegation

  • Programmatic Subagents - using the AgentDefinition class
  • Delegation Logic
  • Least Privilege - minimizing the blast radius of errors

Model Context Protocol (MCP) Integration

  • Connecting to MCP servers
  • Namespace Management
  • MCP Workflows

Security, Sandboxing, and Evals

  • Sandboxing - running Bash and Python tools in containerized environments
  • Validation - using MCP tools for automated template and code validation before deployment
  • Human-in-the-Loop - implementing checkpoints for subagent actions

Build AI Agents with Claude Agent SDK

real world content

Real-World Content

Project-focused demos and labs using your tool stack and environment, not some canned "training room" lab.
expert practitioners

Expert Practitioners

Industry experts that bring their battle scars into the classroom.
experiential learning

Experiential Learning

More coding than lecture, coupled with architectural and design discussions.
fully customized

Tailored Outlines

Once-size-fits-all doesn't apply to training teams. That's where we come in!

Dive in and learn more

When transforming your workforce, it’s important to have expert advice and tailored solutions. We can help. Tell us your unique needs and we'll explore ways to address them.

Let's chat

By clicking submit, you agree to our Privacy Policy and Terms of Use, and consent to receive marketing emails from Pluralsight.
Related Pages