Get in Touch
 Duration 14 hours

Course Outline

Introduction

  • Comparing workflows versus autonomous agents
  • System architecture overview and common application scenarios

Core Concepts of the Claude API

  • Messages API structure, model selection, and parameters
  • Designing system prompts and managing structured outputs
  • Implementing streaming and error management
  • Practical exercise: Initial API integration

Tool Integration

  • Specifying tools and data schemas
  • Mastering the tool-use cycle and error recovery strategies
  • Practical exercise: Creating an agent that interacts with corporate APIs

MCP and Agent Skills

  • Understanding MCP servers and clients
  • Leveraging existing servers and developing custom ones
  • Implementing Agent Skills for reusable domain expertise
  • Practical exercise: Linking an agent to a data source

The Claude Agent SDK

  • Managing agent loops, sessions, and context
  • Configuring permissions, hooks, and sub-agents
  • Practical exercise: Developing a research and reporting agent

Cost, Quality, and Safety

  • Implementing prompt caching and token budgeting
  • Establishing guardrails and human approval workflows
  • Conducting evaluations with a small test dataset
  • Setting up logging and monitoring systems

Transitioning to Production

  • Exploring deployment strategies and secrets management
  • Handling maintenance and version control
  • Formulating a roadmap for participants' specific use cases

Requirements

  • Proficiency in Python or TypeScript
  • Experience with REST API interactions and JSON processing
  • Familiarity with the fundamentals of large language models

Target Audience

  • Software developers and data engineers integrating AI capabilities into products and internal systems
  • Solution architects assessing agent-based architectures
  • Technical teams aiming to transition from prototype stages to production environments

Number of participants


Price per participant

Testimonials (3)

Upcoming Courses

Related Categories