Module 01: Generative AI and Data Foundations

• Understand what artificial intelligence, machine learning and generative AI mean, and how they fit together
• Work with a large language model and write prompts that carry clear instructions, context and the format you need
• Learn why these tools state wrong things confidently, and how to check an answer before you rely on it
• Learn the language of data: rows, columns, records, and the problems that turn up in everyday files

Module 02: Spreadsheet Analysis and Dashboards

• Work confidently in a spreadsheet with cells, ranges and formulas that do the calculating for you
• Clean a messy dataset by handling blanks, duplicates and entries written several different ways
• Summarise data by sorting, filtering and building pivot tables that answer a business question
• Choose the right chart for the question, and build a dashboard you can share

Module 03: SQL for Data Work

• Understand why organisations store data across many tables, and how those tables connect
• Write queries that select the columns you want and filter down to the rows that matter
• Summarise data with counts, totals and averages, grouped by any category you choose
• Combine two tables with a join to answer questions that neither table could answer alone
• Turn a business question into a working query, and produce a report others can read

Module 04: AI-Assisted Analysis and Agents

• Use an AI assistant to summarise and interrogate a dataset, checking every claim against the data itself
• Build a custom AI assistant with standing instructions for a task you repeat often
• Ground an assistant in your own documents so it answers from them rather than from general knowledge, the approach known as retrieval-augmented generation, or RAG
• Build an AI agent that works through a sequence of steps on your behalf, and judge which tasks are safe to hand over

NotebookLM Google AI Studio

Module 05: Python for Data

• Write your first Python code using variables, numbers, text and lists
• Use loops to work through a whole list, counting, totalling and filtering as you go
• Load a dataset with Pandas, inspect what arrived, and select exactly the rows and columns you need
• Filter with conditions, create new columns, and plot distributions and relationships
• Carry out a complete exploratory analysis and write up what you found

Seaborn

Module 06: Foundations of Machine Learning

• Recognise what machine learning is asked to do, and learn why a model is only trusted on data it has never seen
• Build a model that predicts a number, and judge how far its predictions fall from the truth
• Build a model that predicts a category, read a confusion matrix, and choose between precision and recall
• Spot a model that has learned its training data too well, and test it properly with cross-validation
• Take a dataset from preparation through to a working, evaluated model of your own

scikit-learn

Capstone Project

The programme concludes with an independent capstone project, and you choose your track. A data project takes a dataset of your own choosing from cleaning through to findings, presented in language a non-technical reader can follow. A prediction project frames a question as a prediction problem, then builds and evaluates a model and reports honestly on where it works and where it fails. Either way you finish with documented work you can show and explain whenever you need to, including to an employer.