Get in Touch
 Duration 14 hours

Course Outline

Introduction

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

Claude API Fundamentals

  • Understanding the Messages API, models, and parameters
  • Utilizing system prompts and structured output
  • Implementing streaming and error handling
  • Lab: Initial API integration

Tool Use

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

MCP and Agent Skills

  • Exploring MCP servers and clients
  • Integrating existing servers and developing a basic server
  • Leveraging Agent Skills for reusable expertise
  • Lab: Connecting an agent to a data source

Claude Agent SDK

  • Agent loops, sessions, and context management
  • Managing permissions, hooks, and subagents
  • Lab: Building a research and reporting agent

Cost, Quality, and Safety

  • Applying prompt caching and token budgeting
  • Implementing guardrails and human approval steps
  • Conducting evaluations with a small test set
  • Logging and monitoring practices

From Prototype to Production

  • Deployment options and secure secrets handling
  • Maintenance and versioning strategies
  • Creating a roadmap for your specific use case

Requirements

  • Proficiency in Python or TypeScript
  • Hands-on experience with REST APIs and JSON data handling
  • Foundational knowledge of large language models

Target Audience

  • Software developers and data engineers integrating AI features into products and internal tools
  • Solution architects assessing agent-based architectures
  • Technical teams aiming to transition from prototyping to production-ready solutions

Number of participants


Price per participant

Testimonials (3)

Upcoming Courses

Related Categories