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 static workflows and autonomous agents
- High-level architectural views and common application scenarios
Core Concepts of the Claude API
- Exploring the Messages API, available models, and configuration parameters
- Crafting effective system prompts and enforcing structured outputs
- Implementing streaming responses and robust error handling strategies
- Practical Exercise: Setting up your first API integration
Implementing Tool Usage
- Specifying tool definitions and data schemas
- Managing the execution loop and recovering from errors
- Practical Exercise: Creating an agent that interacts with internal company APIs
MCP Integration and Agent Skills
- Understanding MCP server and client architectures
- Leveraging existing server infrastructure and developing lightweight custom servers
- Utilizing Agent Skills to encapsulate and reuse domain expertise
- Practical Exercise: Linking an agent to an external data source
Leveraging the Claude Agent SDK
- Managing agent loops, session states, and context
- Configuring permissions, hooks, and subagent frameworks
- Practical Exercise: Constructing a specialized research and reporting agent
Optimizing Cost, Quality, and Safety
- Applying prompt caching and managing token budgets
- Implementing safety guardrails and human-in-the-loop approval mechanisms
- Running evaluations using concise test sets
- Setting up logging and performance monitoring
Transitioning from Prototype to Production
- Reviewing deployment strategies and secure secret management
- Establishing maintenance schedules and version control practices
- Developing a strategic roadmap for specific use cases
Requirements
- Proficiency in Python or TypeScript
- Hands-on experience with REST API interactions and JSON data processing
- Fundamental knowledge of Large Language Model (LLM) concepts
Target Audience
- Software engineers and data specialists integrating AI capabilities into products or internal systems
- Solution architects assessing agent-based system architectures
- Technical teams transitioning AI solutions from experimental 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
