3-Day Artificial Intelligence Workshop
Analyse • Code • Model • Create • Build • Test • Innovate • Present
The Class 9 AI Adventure Workbook is the most advanced level in the series so far. Students move beyond simply using AI and begin analysing data, writing Python, reasoning about machine-learning models, designing AI systems, testing prototypes and defending their work before judges.
Implementation Note: The learning topics, activities and project concepts below are taken from the Class 9 workbook. Where the workbook does not prescribe a particular software platform, suitable recommended implementation tools have been added for practical workshop execution.
Day 1 — Analyze & Code
AI Thinkers & Python Problem Solvers
Day 1 builds the engineering foundation behind AI.
Students Learn
- What AI can and cannot do
- Human vs machine intelligence
- AI vs Machine Learning vs Deep Learning
- Intelligent systems and feedback
- Algorithms
- Sequence, decision and repetition
- Data → Information → Patterns
- Features and labels
- Training examples
- Classification and recommendation
- Data quality and bias
- Python variables and data types
- Operators
- Input and output
- Lists, indexing and slicing
- if / elif / else
- for and while loops
- Functions, parameters and return values
- Strings and simple text processing
The workbook contains seven Python labs, moving students from variables through text processing and debugging.
Day 1 Activities
Human vs AI • Which Ring? • Algorithm Builder • Feature or Label? • Bias Detective • Design a Mini Dataset • Python Challenges • Review Sorter • Quiz / Marks Analyzer
Students also design a dataset for a real school problem by deciding its features, label, source of data and fairness check.
Day 2 — Explore & Create
Python, Machine Learning & Generative AI
Day 2 moves from writing code to measuring whether AI and machine-learning systems actually work.
Students Learn
- Python data analysis
- Search and pattern-finding
- Student Performance Analysis
- Supervised learning
- Unsupervised learning
- Training and test data
- Classification
- Regression
- Accuracy
- Model errors
- Overfitting and underfitting
- Generative AI
- AI-created text, images, music and video
- Prompt Engineering
- Responsible AI
- Hallucinations and verification
By the end of the day, students are expected to analyse datasets, distinguish classification from regression, recognise overfitting and verify AI claims instead of automatically trusting them.
Prompt Engineering
Students learn the Class 9 four-part prompt framework:
Role + Context + Task + Format
They also learn that a good prompt is normally improved through iteration rather than written perfectly on the first attempt.
Day 2 Activities
Python Data Analysis • Pattern Finding • Student Performance Analyzer • Machine Learning Exercises • Generative AI Studio • Prompt Upgrade Challenge • Prompt Challenge • Responsible AI Activities • Level 2+ AI Quiz
Day 3 — Build & Innovate
AI Builders & Young Innovators
Day 3 turns the learning into a real build.
Students Explore
- Computer Vision
- Image Classification
- Object Detection
- Natural Language Processing
- Intent Recognition
- Sentiment Analysis
- Chatbots
- Robotics
- Internet of Things
- Smart Devices
- System Design
- Flowcharts
- Testing and Debugging
- Prototype Development
- User Feedback
- Young Innovator Pitch
- AI careers and portfolios
Students combine Python, data, machine learning and Generative AI to build something for a real person.
Projects Students Build & Explore
1. Quiz / Marks Analyzer
Students combine their Day 1 Python skills into one program using names and marks.
The project includes:
- Two connected lists
- At least three student-written functions
- Count, highest, lowest, average and spread
- Grades using if / elif / else
- Search by student name
- A data-based piece of advice for the teacher
- Testing for invalid or missing input
Implementation Tools:
Python
Recommended Platform: Replit / Google Colab
2. Review Sorter
Students create a basic text-analysis system that examines real canteen or library reviews and labels them:
Positive • Negative • Unclear
They then record how many reviews their keyword-based system gets wrong, helping them understand the limitations of simple NLP.
Implementation Tools:
Python
Recommended Platform: Replit / Google Colab
3. Student Performance Analyzer
This is a more advanced Python data project.
Students work with three test scores per student and create a report containing:
- Student averages
- Best test score
- Performance trend
- Class average and spread
- Number of students improving
- Search by student name
- Flags for slipping performance or marks below 40
- Error handling for empty or unknown input
The project requires at least four functions with return values.
Implementation Tools:
Python
Recommended Platform: Replit / Google Colab
4. Vision Challenge — Design an Image Classifier
Students design a computer-vision classifier for a real use case.
The workbook example is a system that sorts school waste photographs into:
Paper • Plastic • Food • Other
Students plan:
- The classification job
- 3–5 classes
- Training data
- A separate test set
- Variation in photographs
- What happens when the classifier is wrong
Recommended Implementation Tool:
Google Teachable Machine
Additional Tools:
Phone camera / webcam for collecting images
This allows students to turn the workbook specification into a small working image classifier without needing advanced machine-learning code.
5. Chatbot Designer — Study Assistant
Students design a focused study chatbot rather than a chatbot that tries to answer everything.
They define:
- The exact user
- The problem being solved
- Four intents
- Different ways a student might phrase a question
- The chatbot’s replies
- What happens when it does not understand
- Requests it must refuse
- An honest label telling users they are speaking to a bot
The workbook also contains a Python Intent Matcher using keyword lists and conditions.
Implementation Tools:
Python – for the workbook’s intent-matching logic
Recommended Tools for a richer prototype:
Botpress – structured chatbot building
ChatGPT / Gemini – conversational AI functionality
6. Robot Decision Challenge — Smart Device
Students design a smart device for a real problem in their school or home using:
Sense → Process → Act
They specify:
- Sensors
- Processing and decision logic
- Actuators
- The problem being solved
- A real Python decision rule
- Something the device must never do
The workbook example is a Classroom Air Monitor that uses CO₂, temperature and occupancy data to predict when classroom air is becoming stale.
Recommended Implementation Tools:
micro:bit • MakeCode
Optional Hardware:
Temperature sensor • Light sensor • Distance sensor • LEDs • Buzzer
Computer Vision Exploration
Students learn the computer-vision pipeline:
Image → Features → Model → Prediction
They also distinguish between:
Image Classification — assigning one label to the whole image
and
Object Detection — finding objects and identifying where they appear in an image.
Recommended Implementation Tools:
Google Teachable Machine – image classification
Phone / Webcam – training and test images
NLP & Chatbot Exploration
Students learn how AI handles language through:
Question → Processing → Intent → Response
They explore:
- Keyword spotting
- Sentiment analysis
- Text classification
- Intent recognition
- Chatbot responses
The workbook directly connects these concepts to Python string methods such as .lower(), .strip() and .split().
Implementation Tools:
Python – keyword matching and sentiment activities
Recommended: Botpress / ChatGPT / Gemini for conversational prototypes
Creative Generative AI Activities
AI Text Creation
Students explore Generative AI for explanations, summaries, drafts, quiz questions and Python code.
Recommended Tools:
ChatGPT • Claude • Gemini
AI Image Creation
Students explore AI-generated illustrations, posters, diagrams and concept art.
Recommended Tools:
DALL·E • Canva AI
AI Music Creation
Students explore creating backing tracks and jingles by describing style, tempo and instruments.
Recommended Tool:
Suno
AI Video Creation
Students explore creating short video clips from written scene descriptions.
Recommended Tool:
Runway
Final Project — AI Innovation Challenge
The main Class 9 project is an 11-step AI Innovation Challenge.
Students have three hours to turn a real problem into a working prototype.
The 11-Step Process
1. Find the Problem
Choose a real, specific and recurring problem.
2. Define the User
Identify and speak to a real person.
3. Write the Problem Statement
4. Design the Solution
Decide what AI should actually do.
5. Plan Input → Process → Output
6. Choose the Technology
7. Build the Prototype
8. Test It
9. Get Feedback
Use someone outside the team.
10. Improve It
11. Present It
The workbook makes an important distinction: students should choose one suitable technology, rather than adding AI simply to make the project look advanced.
Suggested Implementation Tools for the Innovation Challenge
The workbook allows projects based on Python, no-code AI, Generative AI, computer vision, NLP or even a paper prototype.
Suitable practical tools include:
Python / Data Project: Replit or Google Colab
Image Classifier: Google Teachable Machine
Chatbot / NLP: Python, Botpress, ChatGPT or Gemini
Smart Device / Robotics: micro:bit + MakeCode
Generative Text: ChatGPT / Claude / Gemini
AI Images: DALL·E / Canva AI
Presentation: Canva / Google Slides
Prototype Design: Figma / Canva
Image Data: Phone camera / webcam
Young Innovator Pitch
Students present their final prototype in a four-minute pitch, followed by questions from the judges.
The pitch contains five sections:
1. Problem
Whose problem is it?
2. Solution
Explain the idea in one clear sentence.
3. How It Works
Run the prototype, code or AI model live.
4. Benefits
Explain who benefits and how success can be measured.
5. Future
Explain improvements, limitations and responsible use.
Projects are judged on:
Problem Clarity • AI Usefulness • Technical Understanding • Prototype/Demo • Creativity • Teamwork • Presentation
Skills Students Develop
Through the three-day programme, students develop:
AI & Machine Learning Understanding • Python Programming • Algorithms • Data Analysis • Data Quality & Bias Awareness • Classification & Regression • Model Accuracy • Train/Test Evaluation • Overfitting Awareness • Prompt Engineering • Generative AI Skills • Computer Vision • NLP & Chatbot Design • Robotics & IoT Thinking • Testing & Debugging • Responsible AI Use • Prototype Development • Teamwork • Presentation Skills
By the end, students are expected to have designed an AI solution to a real problem, built and tested a prototype, demonstrated it working and defended their decisions before others.
Analyse → Code → Model → Create → Build → Test → Innovate → Present
3 Days. From Using AI to Engineering With It.
The workshop concludes with the AI Innovation Challenge, Young Innovator Pitch, Project Exhibition, Grand Finale and Certificate of Completion. The Class 9 certificate records learning across Python, data and bias, machine learning, Generative AI, prompt engineering, computer vision, NLP, robotics and project development.
SKK Educational Foundation
AI + Python + Machine Learning + Generative AI + Project Innovation