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 use cases.
Foundations of the Claude API
- Details on the Messages API, available models, and parameters.
- Crafting system prompts and generating structured output.
- Implementing streaming and error management.
- Lab: Initial API integration exercise.
Tool Utilization
- Defining tools and their corresponding schemas.
- The mechanics of the tool-use loop and strategies for error recovery.
- Lab: Developing an agent that interacts with company-specific APIs.
MCP and Agent Skills
- Understanding MCP servers and clients.
- Leveraging existing servers and developing a custom one.
- Implementing Agent Skills for reusing specialized knowledge.
- Lab: Connecting an agent to an external data source.
The Claude Agent SDK
- Managing the agent loop, sessions, and context.
- Configuring permissions, hooks, and subagents.
- Lab: Creating a research and reporting agent.
Cost Efficiency, Quality, and Safety
- Applying prompt caching and managing token budgets.
- Establishing guardrails and human approval workflows.
- Conducting evaluations with a small test dataset.
- Implementing logging and monitoring solutions.
Transitioning from Prototype to Production
- Exploring deployment options and managing secrets securely.
- Addressing maintenance and version control.
- Creating a roadmap for participants' specific use cases.
Requirements
- Programming proficiency in Python or TypeScript.
- Experience with invoking REST APIs and managing JSON data.
- A foundational understanding of large language models.
Target Audience
- Software developers and data engineers integrating AI capabilities into products or internal tools.
- Solution architects assessing agent-based architectures.
- Technical teams aiming to transition from prototypes to production-ready systems.
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
