Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Introduction
- Distinguishing between workflows and autonomous agents
- Overview of architecture and common application scenarios
Core Claude API Concepts
- Exploring the Messages API, available models, and configuration parameters
- Crafting system prompts and handling structured output
- Managing streaming responses and error scenarios
- Practical Session: Initial API integration
Implementing Tool Use
- Setting up tools and defining their schemas
- Understanding the tool-use loop and strategies for error recovery
- Practical Session: Building an agent that interfaces with company APIs
MCP and Agent Skills
- Understanding MCP servers and client interactions
- Leveraging existing servers and creating simple custom ones
- Utilising Agent Skills for reusable expertise
- Practical Session: Linking an agent to a specific data source
The Claude Agent SDK
- Managing the agent loop, sessions, and context
- Configuring permissions, hooks, and subagents
- Practical Session: Developing a research and reporting agent
Cost, Quality, and Safety
- Applying prompt caching and token budgeting strategies
- Implementing guardrails and human-in-the-loop approval steps
- Conducting evaluations using a focused test set
- Setting up logging and monitoring systems
Transitioning from Prototype to Production
- Evaluating deployment options and managing secrets securely
- Handling maintenance and version control
- Developing a roadmap for your specific use case
Requirements
- Programming proficiency in Python or TypeScript
- Familiarity with invoking REST APIs and processing JSON
- A foundational understanding 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 seeking to transition from prototypes to production environments
Testimonials (3)
The trainer is patient and very helpful. He knows the topic well.
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
Course - Agentic AI for Business Automation: Use Cases & Integration
Good mixvof knowledge and practice
Ion Mironescu - Facultatea S.A.I.A.P.M.
Course - Agentic AI for Enterprise Applications
The mix of theory and practice and of high level and low level perspectives
