Course Details
Course Details
What You'll Learn
Topic 1: Overview of Agentic AI in Gemini ADK
Topic 2: Build A Multi Agent App with Gemini ADK
Topic 3: Build Agentic AI RAG in Gemini ADK
Topic 4: Build an Agentic AI App with Gemini Agent ADK and Streamlit
Course Info
Minimum Entry Requirement
Knowledge and Skills
- Able to operate using computer functions
- 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.
Target Age Group: 18-65 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
Job Roles
Job Roles
- AI Solutions Architect
- Machine Learning Engineer
- Multi-Agent Systems Developer
- AI Platform Engineer
- Conversational AI Developer
- LLM Application Developer
- AI Integration Specialist
- Agentic AI Engineer
- AI Product Manager
- Natural Language Processing Engineer
- AI Automation Engineer
- Cloud AI Engineer
- AI DevOps Engineer
- Intelligent Systems Designer
- AI Research Engineer
- Full Stack AI Developer
- AI Infrastructure Engineer
- Chatbot and Virtual Agent Developer
- AI Technical Consultant
- Enterprise AI Developer
Trainers
Trainers
Multi-agent system design is the centre of Dr. Alfred Ang's engineering work. A full-stack AI developer and Agentic AI solution architect, he specialises in collaborative, goal-driven agent architectures for real enterprise use cases, and he builds them with the Google Gemini Agent SDK alongside the OpenAI Agents SDK, the Claude Agent SDK, Microsoft AutoGen, CrewAI, n8n, Langflow and Flowise. He serves as Managing Director, CIO, CTO and Chief Instructional Designer of Tertiary Infotech Academy Pte Ltd and founded Tertiary Courses, where he leads agentic AI adoption across customer service, internal workflows, analytics and decision support using LLMs, RAG pipelines and multi-agent systems. His GitHub portfolio of more than 300 public repositories includes several projects built on Gemini: n8n-ragdemo, a no-code RAG demonstration in which a Telegram AI agent running on Gemini answers questions from uploaded PDFs; bakerycourses-demo, a lead-magnet site with a Gemini course chatbot that deliberately uses context-stuffing instead of RAG; and logomaker, which generates logo options with Gemini image models. He has also built Streamlit applications such as wsq-courseware-generator-claude-streamlit, an AI-powered courseware platform, and data-mining-ml-labs, a set of interactive Python labs. He is a Microsoft Certified AI Engineer Associate (AI-102) and Data Scientist (DP-100), an AWS Certified Solutions Architect and AI Practitioner, and holds a PhD in Electrical Engineering from NUS. He also holds a Graduate Diploma in Intelligent Robotics Systems from NUS-ISS and the Certificate in AI Ethics and Governance (Senior Professional) from NTU.
In Building Multi Agent Aplications with Gemini ADK, Dr. Ang guides developers and technical professionals from first principles to a deployed application. The course opens with an overview of agentic AI in Google's Agent Development Kit: how an agent reasons, chooses tools and hands work to other agents. Learners then build a multi-agent app, defining specialist agents and the coordinator that routes tasks between them, before adding agentic RAG so agents can retrieve knowledge from documents instead of guessing. The final topic brings everything together in an agentic AI application with a Streamlit front end, the same pairing he uses in his own tools, so learners finish with something they can demonstrate and extend. His experience of comparing RAG with simpler context-stuffing helps learners choose the right retrieval approach for their data rather than defaulting to the most complex one. He pays close attention to the practical details that decide whether a multi-agent system is reliable: clear agent instructions, well-scoped tools, sensible hand-offs, and testing each agent before wiring the team together. Code is built live and step by step, with time for learners to adapt each example to their own use case. As an ACTA-certified trainer and DACE-certified curriculum developer, he keeps complex material structured and approachable. He also discusses how to log and trace agent hand-offs, so that when a multi-agent app gives a poor answer, learners can find which agent caused it. To explore the Gemini and multi-agent projects behind his teaching, visit his GitHub portfolio at https://github.com/alfredang and connect with him on LinkedIn at https://www.linkedin.com/in/angchewhoe/
Solomon Soh is a data scientist and AI trainer and a Certified AI Engineer Associate by AI Singapore, with interests in natural language processing, reinforcement learning and time-series analysis. As a Data Science Trainer with IBM Singapore, he has coached teams on projects involving NLP, computer vision and chatbots, earning a 96% learner satisfaction rating. He is ACTA-certified, holds Alibaba Cloud Architect and Alteryx certifications, and has trained and coached over 100 professionals in data science, Python programming and coding. His industry work at Workforce Optimizer, Certis Cisco, Ernst & Young and IQVIA centred on Python-driven analytics.
In this Gemini ADK course, Solomon applies his Python and chatbot project experience to Google's open-source Agent Development Kit. Learners get an overview of agentic AI in Gemini ADK, build a multi-agent app, create an agentic RAG solution that grounds answers in their own data, and then build a complete agentic AI app with Gemini ADK and Streamlit. He helps learners understand how agents reason, use tools and hand work to one another, so they can structure their applications deliberately rather than by trial and error. Participants leave able to design, build and deploy multi-agent applications powered by Gemini models.
Quah Chee Yong is an ACLP-certified trainer and data science professional with extensive experience in Python, natural language processing (NLP) and machine learning. He has led AI training programmes for SAP, Temasek Polytechnic and IMDA under the SGUnited Mid-Career Pathways initiative. He has delivered corporate workshops on chatbot development, recommender systems and text analytics, and applies NLP tools such as NLTK, spaCy and Gensim to sentiment analysis, topic modelling and text classification. Alongside this, he has equipped himself with skills in deep learning and cloud deployment, and brings experience from technical, operations and commercial positions across several industries. He is a Singapore WSQ-certified Adult Educator.
In Building Multi Agent Applications with Gemini ADK, he brings his Python, NLP and chatbot background to applications in which several AI agents reason, use tools and work together. Learners begin with an overview of agentic AI in Google's Agent Development Kit, build a multi-agent app, add retrieval-augmented generation to create an agentic RAG solution, and finish by building an agentic AI app with Gemini ADK and Streamlit. His experience teaching both technical and non-technical learners helps participants grasp how agents divide work and retrieve knowledge, so they can design and deploy multi-agent applications for their own use cases.
Teh Siew Yee is a seasoned data science and digital transformation leader with more than two decades of experience spanning organisational strategy, talent development and the design of data ecosystems across Asia Pacific and global markets. Siew Yee has hands-on experience in data architecture, engineering and analytics, and expertise in predictive modelling, machine learning and deep learning. Having led cross-geographical teams, Siew Yee has worked across the technology, education, finance, aerospace and eCommerce sectors. Siew Yee is also an ACLP-certified trainer who has built digital transformation programmes for learners ranging from the C-suite to working-level employees.
In this course, Siew Yee brings that machine learning and data engineering experience to building multi-agent applications with Google's Agent Development Kit (ADK) and Gemini models. Learners begin with an overview of agentic AI in Gemini ADK, then build a multi-agent app in which specialised agents reason, use tools and collaborate. They go on to create an agentic RAG application that retrieves knowledge from documents, and finish by packaging an agentic AI app with a Streamlit interface that others can use. Through guided, hands-on practice, Siew Yee helps participants move from concept to a working multi-agent application they can adapt for their own business scenarios.
Alfred Yap is an ACLP-certified trainer whose closest expertise for this course is cloud computing and information technology. He is an IBM Certified Cloud Computing Practitioner and an IBM Enterprise Design Thinking Practitioner, and his current interests include cloud computing, cyber security and blockchain. Alfred began his teaching career as a trainer for Oracle University and has taught adult learners since the 1990s, conducting ICT-related training for companies in the consulting, media and training industries. He holds an undergraduate degree from USF in America and a master's degree in Knowledge Management from NTU, Singapore, and he has a strong foundation in instructional design and applied learning.
In Building Multi Agent Applications with Gemini ADK, Alfred brings his cloud and IT background to Google's Agent Development Kit and Gemini models. Learners start with an overview of agentic AI in Gemini ADK, then build a multi-agent app, develop an agentic AI RAG solution, and finally create an agentic AI app with Gemini ADK and Streamlit. His design thinking practice helps learners frame each agent's role around a clear user need, while his security training encourages careful handling of data and access. Participants leave with hands-on experience designing, building and deploying agents that reason, use tools and collaborate.
Review
Customer Reviews (2)
- will recommend Review by Course Participant/Trainee
-
Programme is good, covers both theory and codes. Codes are useful for application. (Posted on 4/20/2020)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 - Will Recommend Review by Course Participant/Trainee
-
Add some more machine learning forecasting elements (Posted on 8/27/2019)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