Get in Touch
 Duration 14 hours

Course Outline

Introduction

  • Distinguishing between workflows and agents
  • Overview of architecture and common use cases

Claude API Basics

  • Exploring the Messages API, available models, and parameters
  • Implementing system prompts and structured outputs
  • Handling streaming responses and errors
  • Lab: Initial API integration

Tool Utilization

  • Specifying tools and defining schemas
  • Managing the tool-use loop and error recovery mechanisms
  • Lab: Creating an agent that interacts with internal company APIs

MCP and Agent Skills

  • Understanding MCP servers and clients
  • Leveraging existing servers and developing a simple custom server
  • Implementing Agent Skills for reusable expertise
  • Lab: Linking an agent to an external data source

Claude Agent SDK

  • Managing the agent loop, sessions, and context
  • Configuring permissions, hooks, and sub-agents
  • Lab: Constructing a research and reporting agent

Cost, Quality, and Safety

  • Implementing prompt caching and managing token budgets
  • Establishing guardrails and human approval workflows
  • Running evaluations using a small test set
  • Setting up logging and monitoring systems

Transitioning from Prototype to Production

  • Reviewing deployment options and managing secrets securely
  • Managing maintenance and version control
  • Creating a roadmap for the participant's specific use case

Requirements

  • Programming proficiency in either Python or TypeScript
  • Experience with REST API calls and JSON data handling
  • Familiarity with the fundamentals of large language models

Target Audience

  • Software developers and data engineers integrating AI features into products or internal tools
  • Solution architects assessing various agent architectures
  • Technical teams aiming to transition from prototype stages to production environments

Number of participants


Price per participant

Testimonials (3)

Upcoming Courses

Related Categories