Get in Touch
 Duration 14 hours

Course Outline

Introduction

  • Differences between workflows and agents
  • Architectural overview and common use cases

Basics of the Claude API

  • Messages API, available models, and key parameters
  • System prompts and structured outputs
  • Streaming mechanisms and error handling
  • Lab: Initial API integration

Tool Usage

  • Defining tools and their schemas
  • The tool-use loop and error recovery strategies
  • Lab: Creating an agent that interacts with corporate APIs

MCP and Agent Skills

  • MCP servers and client implementations
  • Utilizing existing servers and developing a simple custom server
  • Agent Skills for reusing specialized knowledge
  • Lab: Connecting an agent to a data source

Claude Agent SDK

  • Agent loops, session management, and context control
  • Permissions, hooks, and subagent configuration
  • Lab: Developing a research and reporting agent

Cost, Quality, and Safety

  • Prompt caching and token budgeting
  • Implementing guardrails and human approval steps
  • Evaluating performance with a small test set
  • Logging and monitoring practices

From Prototype to Production

  • Deployment strategies and secret management
  • Maintenance and versioning practices
  • Roadmap planning for participants’ specific use cases

Requirements

  • Programming proficiency in Python or TypeScript
  • Experience with REST API calls and JSON handling
  • A foundational understanding of large language models

Audience

  • Software developers and data engineers integrating AI features into products and internal tools
  • Solution architects assessing agent-based architectures
  • Technical teams seeking to transition from prototypes to production environments

Number of participants


Price per participant

Testimonials (3)

Upcoming Courses

Related Categories