Course Details
Course Details
What You'll Learn
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 Systems
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
Assessment
- Written Exam
- Practical Exam
- Oral Questioning
Course Info
Minimum Entry Requirement
Knowledge and Skills
- Able to operate using 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
Minimum Software/Hardware Requirement
Software:
You will need the following for this course:
- Python 3 – free
- Visual Studio Code – free
- A free Google Gemini API key – from Google AI Studio
Hardware: Windows PC or Mac laptop
Funding Eligibility Criteria
Self-sponsored learners (individuals)
- Singapore Citizens and Singapore Permanent Residents aged 21 and above.
- Up to 50% course fee funding. Singapore Citizens aged 40 and above receive up to 70% under the Mid-career Enhanced Subsidy (MCES).
- Singapore Citizens aged 25 and above can pay the remaining fee with SkillsFuture Credit.
Company-sponsored learners
- Singapore Citizens and Singapore Permanent Residents who are direct employees of the sponsoring company.
- Up to 50% course fee funding, or up to 70% for employees of SMEs (Enhanced Training Support for SMEs) and for Singapore Citizens aged 40 and above. An SME has no more than 200 employees or an annual turnover of no more than $100 million.
- Employers can also claim Absentee Payroll funding for employees who attend during working hours.
- Eligible companies can offset their out-of-pocket fees with SkillsFuture Enterprise Credit (SFEC).
Conditions for all funded learners
- Attendance is taken digitally with Singpass for every session, including the assessment.
- You must complete the course and pass all assessments (assessed as Competent).
- If these conditions are not met, the funding is clawed back and the learner or employer pays the full course fee.
- 9% GST is charged on the full course fee before funding.
- Promo and discount codes cannot be used on funded courses.
- Any balance after funding can be paid in cash, with SkillsFuture Credit, with PSEA (Singapore Citizens with a PSEA), or partly reimbursed by UTAP for NTUC members.
How to Apply SkillsFuture Credit Claim for Individuals
Singapore Citizens aged 25 and above can use their SkillsFuture Credit (base tier) to pay the course fee after funding. The $4,000 mid-career top-up cannot be used for this course.
- Register for this course as self-sponsored and tell us you will use SkillsFuture Credit. Do not pay the amount you plan to claim.
- We email you an invoice showing the course fee after funding.
- From 60 days before the course starts, and no later than the course start date, log in to MySkillsFuture with Singpass and click Claim credits.
- Click Submit a Claim and search for this course by its course code, TGS-2020503207.
- Select your class start date, enter the course fee payable after funding and the amount of credit to claim, then upload the invoice (PDF, JPG or PNG, under 4MB).
- Review, accept the terms and click Agree and Submit. The credit is paid directly to us; processing can take up to 14 working days.
Changing or withdrawing: cancel the claim on MySkillsFuture at least one day before the course starts. If your class date changes, cancel the claim and submit a new one with the new date.
How to Apply SkillsFuture Enterprise Credit (SFEC)
SFEC helps companies pay for employee training. The current SFEC ends on 30 November 2026, and a redesigned SFEC starts on 1 December 2026.
Current SFEC: classes ending on or before 30 November 2026
- Eligible companies received a one-off $10,000 credit, notified by letter to their Corppass administrator. Eligibility generally required at least 3 Singapore Citizen or PR employees and Skills Development Levy contributions.
- SFEC covers up to 90% of the company's out-of-pocket course fee after other subsidies.
- Check your company's SFEC eligibility and balance on EnterpriseSG.
- Register your Singapore Citizen or PR employee for a class that ends by 30 November 2026, as company-sponsored, and pay the course fee after funding.
- Your employee attends and completes the course. We submit the attendance and assessment results to SWDA.
- No separate claim is needed. SFEC is calculated automatically once the course fee grant is approved and is paid quarterly to your company's IRAS GIRO or PayNow Corporate account.
Any unused balance of the current SFEC expires on 30 November 2026.
Redesigned SFEC from 1 December 2026
Companies with at least 3 resident employees receive a fresh $10,000 in an online SFEC wallet that offsets out-of-pocket fees upfront at enrolment, instead of reimbursing them afterwards. SWDA has not yet published the support rates and claim steps; see OurWorkforce or our SFEC guide.
How to Apply UTAP (NTUC Members)
NTUC members can claim 50% of the unfunded course fee under the Union Training Assistance Programme (UTAP), capped at $250 a year (aged below 40) or $500 a year (aged 40 and above). The cap is shared with UTAP claims for AI tool subscriptions.
Eligibility: you must be an NTUC member paying full membership fees, with your membership paid up before and during the course and when you claim. The course must not be fully paid for by your employer or another source.
- Make sure your NTUC membership is paid up before the course starts.
- Register for this course with us and pay the course fee after funding and SkillsFuture Credit.
- Attend at least 75% of the course and sit all assessments.
- Within 6 months after the course ends, go to the NTUC U Portal, open UTAP under E-services, log in with Singpass and choose Course Fee Claim.
- Enter the nett course fee you paid (after all subsidies and SkillsFuture Credit, including GST), and upload your invoice or receipt and your certificate or result slip (PDF, JPG or PNG, up to 5MB each).
- NTUC usually pays the claim within 4 weeks of submission.
Read more in our UTAP guide.
How to Apply PSEA
Singapore Citizens with a Post-Secondary Education Account (PSEA), which stays open until around the year you turn 31, can use it to pay the course fee after funding for PSEA-approved courses. You can also use a sibling's PSEA after your own has been used up.
- Check that this course shows the PSEA tag on its MySkillsFuture page.
- Check your PSEA balance on MOE's Student Finance System with Singpass.
- Download and complete the PSEA withdrawal form, then submit it to us.
- We submit the withdrawal request to MOE. You (and your sibling, if you are using their account) authorise it in the Student Finance System. Nothing is withdrawn without this authorisation.
- MOE pays us directly. If you have already paid, we refund the amount covered by PSEA.
More details: MOE PSEA overview.
Appeal Process
If you disagree with an assessment decision, you have the right to appeal.
- When the assessor gives you feedback, say whether you agree with the outcome. If you agree, you and the assessor sign the Assessment Summary Record; if you disagree, do not sign it.
- Discuss the decision with the assessor or the assessment manager first.
- If you are still not satisfied, tell the assessor you intend to appeal. The assessor records this in the feedback section of the Assessment Summary Record and informs the assessment manager.
- Lodge your appeal within 7 days, giving your reasons, using the Candidate Appeal Form. The assessor can help you write and lodge it.
- An Assessment Appeal Panel reviews the information from you and the assessor and makes a decision. A record of the appeal and its outcome is kept.
- You will be told the outcome within 2 weeks of lodging the appeal. The panel's decision is final.
Job Roles
Job Roles
- AI Developer
- Machine Learning Engineer
- Data Scientist
- AI Software Engineer
- Deep Learning Engineer
- Computer Vision Engineer
- NLP Engineer
- Data Analyst
- AI Research Assistant
- AI Solutions Architect
- Software Developer (AI focus)
- Research Engineer (Machine Learning)
- Business Intelligence Analyst
- Robotics Engineer
- AI Product Developer
- Chatbot Developer
- Automation Engineer
- Predictive Analytics Specialist
- Model Validation Analyst
- Technology Innovation Specialist
Trainers
Trainers
Multi-agent system design is the centre of Dr. Alfred Ang's engineering work, and vibe coding is how he builds much of it. A full-stack AI developer and Agentic AI solution architect, he is Managing Director, CIO, CTO and Chief Instructional Designer of Tertiary Infotech Academy Pte Ltd, where he designs Skills Framework-aligned WSQ programmes in AI and modern application development. He builds collaborative, goal-driven agent architectures with the OpenAI Agents SDK, the Google Gemini Agent SDK, the Claude Agent SDK, Microsoft AutoGen, CrewAI and n8n, and deploys them on cloud-native stacks across AWS, Kubernetes and DevOps pipelines. He holds a PhD in Electrical Engineering from NUS, a Graduate Diploma in Intelligent Robotics Systems from NUS-ISS, and certifications including Microsoft Certified AI Engineer Associate (AI-102) and AWS Certified Solutions Architect. His public GitHub portfolio of 300+ repositories shows the techniques taught here in practice: published collections of agent skills for Claude Code that package reusable capabilities; an AI-powered courseware generation platform built with the Claude Agent SDK and Streamlit; a Streamlit app that generates SOP documents for training providers; and an ERP prototype in which AI agents handle purchase orders with human-in-the-loop approvals across email, Asana and Telegram. He has also worked in the defence, electronics and semiconductor industries and co-invented more than 20 US patents. As an ACTA-certified trainer and DACE-certified curriculum developer, he turns cutting-edge agent engineering into structured, assessable learning for working professionals without losing its hands-on character.
In this WSQ course, Dr. Ang takes learners from the foundations of a modern AI agent to a deployed multi-agent system. They explore agent skills as modular, transferable capabilities, agent memory and the fundamentals of the Model Context Protocol (MCP), then learn a structured vibe coding workflow in which context engineering makes AI-generated code and agent behaviour reliable instead of unpredictable. The hands-on core of the course has learners design agents with the OpenAI Agent SDK, using structured outputs, API tool calling and supervisor routing with sub-agent delegation, then build a second collaborative system with the Gemini Agent SDK, deploying both to Streamlit. A deep dive into MCP and sub-agents shows how tool orchestration scales across many agents. Because he builds and ships agent systems himself, he is frank about failure modes such as looping agents, vague tool descriptions and runaway context, and shows how to diagnose and fix them. Learners leave with working, deployed multi-agent applications and a repeatable vibe coding workflow for their next project. He also covers how to version prompts, skills and agent configurations alongside code, how to test agent behaviour with representative inputs, and how to keep secrets and API keys out of repositories. Learners are encouraged to adapt the course projects to a problem from their own work, so the multi-agent systems they build have practical value beyond the classroom. To explore the agent skills and Streamlit applications he has published, view his GitHub portfolio at https://github.com/alfredang and connect with him on LinkedIn at https://www.linkedin.com/in/angchewhoe/
Solomon Soh Zhe Hong is a data scientist and AI trainer with deep expertise in advanced machine learning and deep learning applications. At IBM Singapore he supervised 24 machine learning and deep learning projects, including natural language processing, computer vision and chatbot solutions, earning a 96% learner satisfaction rating. At Workforce Optimizer and Certis Cisco he applied reinforcement learning, forecasting and optimisation models using TensorFlow, scikit-learn and other frameworks. Certified as an AI Engineer and TensorFlow Developer, he has been lead instructor for data science bootcamps and corporate training across Asia.
In WSQ AI Vibe Coding for Multi Agents System, Solomon brings this applied AI and project supervision experience to the design of collaborative agents. Learners explore modern agent foundations, including agent skills, memory systems and Model Context Protocol (MCP) fundamentals, then apply a structured vibe coding workflow and context engineering. They build collaborative multi-agent systems with the OpenAI Agent SDK and the Gemini Agent SDK, using structured outputs, tool calling and supervisor routing, deploy them to Streamlit, and finish with MCP tool orchestration and hierarchical sub-agent design. Combining technical depth with practical teaching, Solomon ensures participants leave able to design, build and deploy multi-agent AI systems that deliver measurable impact.
Quah Chee Yong is an ACLP-certified trainer with strong expertise in machine learning, natural language processing and AI solution development. He has served as Data Science Training Lead at MSITEK, delivering AI programmes for SAP, Temasek Polytechnic and IMDA, and was previously AI Solutions Lead at AiDeal Scan, where he developed recommender systems, NLP-driven search algorithms and customer analytics using TensorFlow and Keras. He also headed the data science team at GoWild Singapore, building analytics platforms and AI-powered digital assistants.
In WSQ AI Vibe Coding for Multi Agents System, his experience building AI-powered digital assistants gives learners a practical anchor for multi-agent design. Participants explore modern agent foundations, including agent skills, memory systems and Model Context Protocol (MCP), then apply a structured vibe coding workflow with context engineering. They build collaborative multi-agent systems with the OpenAI Agent SDK and the Gemini Agent SDK, using structured outputs, tool calling and supervisor routing, deploy them to Streamlit, and finish with MCP tool orchestration and hierarchical sub-agent design. His teaching to both technical and non-technical learners keeps these concepts approachable and hands-on.
Dr Alvin Ang is an ACLP-certified data science and AI trainer with a PhD in Operations Research from Nanyang Technological University. With over a decade of academic and industry experience, he has taught machine learning, deep learning and data science at NTU, SUSS and Curtin University, and as an IBM Data Science Instructor. He holds multiple IBM certifications in TensorFlow, machine learning and applied Python, and he founded the open-source data science community DataFrens.sg. He specialises in guiding learners through advanced machine learning workflows, from data preprocessing to neural network design and deployment.
In WSQ AI Vibe Coding for Multi Agents System, Dr Ang brings this applied AI and deployment experience to the design of collaborative AI agents. Learners explore modern agent foundations, including agent skills, agent memory and Model Context Protocol (MCP) fundamentals, then apply a structured vibe coding workflow and context engineering. They build collaborative multi-agent systems with the OpenAI Agent SDK and the Gemini Agent SDK, covering structured outputs, tool calling and supervisor routing, deploy them to Streamlit, and finish with a deep dive into MCP, tool orchestration and hierarchical sub-agent designs. His hands-on, case-based teaching helps participants leave able to design, build and deploy multi-agent systems for real business challenges.
Terence Ee is an IT leader and independent consultant who, since 2017, has delivered training in Python programming, data analytics and machine learning. Before that he built more than 25 years of experience in technology management, enterprise systems and digital transformation, holding senior roles as Chief Information Officer at the Supreme Court of Singapore and Vice President of Information Systems at Senoko Energy, where he oversaw large-scale IT strategy and system implementation. He holds academic qualifications in Computer Science from NUS and Technology Management from Staffordshire University, and is an ACLP-certified, WSQ-accredited trainer.
In this course, Terence connects his Python and machine learning teaching with his enterprise systems experience to help learners design multi-agent systems that behave reliably. Participants explore modern agent foundations, including agent skills, memory systems and the Model Context Protocol, then learn a structured vibe coding workflow and context engineering techniques. They build collaborative multi-agent systems with both the OpenAI Agent SDK and the Gemini Agent SDK, using structured outputs, tool calling and supervisor routing to sub-agents, deploy them to Streamlit, and finish with a deeper look at MCP tool orchestration and hierarchical agent design. Bridging strategic insight with hands-on technical training, he helps participants judge where multi-agent designs genuinely add value.
Review
Customer Reviews (11)
- Mr. Alfred Ang is a professional and excellent trainer. He is patience and will check on our daily progress regularly. I learned a lot from him during these 2 days course. Review by Course Participant/Trainee
-
Ensure that all the resources are inside the Google Classroom1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment
(Posted on 8/4/2021) - will recommend Review by Course Participant/Trainee
-
. (Posted on 8/2/2021)1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment - might recommend Review by Course Participant/Trainee
-
More practice before the exam1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment
Computer test instead of paper test (Posted on 5/3/2021) - might recommend Review by Course Participant/Trainee
-
the laptop is too slow1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment
more practical session before exam (Posted on 5/3/2021) - will recommend Review by Course Participant/Trainee
-
. (Posted on 8/2/2020)1. Do you find the course meet your expectation? 2. Do you find the trainer knowledgeable in this subject? 3. How do you find the training environment
Write Your Own Review
- Recommended Courses
- Related Courses