AI Vibe Coding for Multi Agents System
About This Course
This WSQ-certified course equips you with the skills to design, build, and deploy multi-agent AI systems using modern vibe coding techniques. You will explore the foundations of AI agents, including agent skills as modular transferable capabilities, agent memory systems, and Model Context Protocol (MCP) fundamentals. Through hands-on projects, you will learn structured vibe coding workflows, context engineering for reliable agent behavior, and how to move from single-agent capability to powerful multi-agent collaboration.
Using both the OpenAI Agent SDK and Gemini Agent SDK, you will build collaborative multi-agent systems with structured outputs, API tool calling, supervisor routing, and sub-agent delegation. The course covers designing hierarchical and sub-agent systems, deep dives into MCP and tool orchestration, and deploying your completed systems to Streamlit. You will also develop competencies in CNN models for image recognition, diagnosing and overcoming overfitting issues, functional API coding, transfer learning for fine-tuning models, and RNN models with word embedding for text recognition.
What You'll Learn
- Understand and code CNN models for image recognition
- Diagnose overfitting issues in image recognition and propose methods to overcome the issues.
- Perform functional API coding based on a selected model.
- Implement transfer learning to fine tune the image recognition models.
- Understand code RNN models and word embedding for text recognition
Topics Covered
Topic 1: Modern Agent Foundations
What is a modern AI agent
Agent skills as modular transferable capabilities
Agent memory systems
Model Context Protocol (MCP) fundamentals
From single-agent capability to multi-agent collaboration
Topic 2: Vibe Coding for Multi-Agent Sytems
What is vibe coding
Structured vibe coding workflow
Context engineering for reliable behavior
Overview of Vibe Coding tools
Adding agent skills
Topic 3: Build a Multi-Agent System with OpenAI Agent SDK
Designing an agent with OpenAI Agent SDK
Structured outputs and API tool calling
Supervisor routing and sub-agent delegation
Build a collaborative multi-agent system
Deployment to streamlit
Topic 4: Build a Multi-Agent System with Gemini Agent SDK
Designing an agent with Gemini Agent SDK
Build a collaborative multi-agent system
Deployment to streamlit
Topic 5: MCP and Sub-Agents
Deep dive into MCP and tool orchestration
Designing hierarchical and sub-agent systems
Entry Requirements
Knowledge and Skills
• Able to operate computer functions with minimum Computer Literacy Level 2 based on ICAS Computer Skills Assessment Framework
• Minimum 3 GCE ‘O’ Levels Passes including English or WPL Level 5 (Average of Reading, Listening, Speaking & Writing Scores)
Attitude
• Positive Learning Attitude
• Enthusiastic Learner
Experience
• Minimum of 1 year of working experience.
• Minimum 18 years old