DS403
Python the Generative Way: From Data to Product
Faculty
Maxim Musin
CEO at rebels.ai
Course length
Duration
Total hours
Credits
Language
Course type
Fee for single course
Fee for degree students
Skills you’ll learn
Overview
Modern Python sits at the core of the AI revolution, and this course follows a single arc: from data to product. In the first half, students use precise data science — with pandas and NumPy at the centre — to extract information from user-behaviour data and audience analysis, and turn it into user understanding: who users are, what they actually do, and where they struggle. That user understanding becomes the foundation for product building.
In the second half, we deep-dive into AI-assisted development: building software collaboratively with modern AI agents. We work with spec-driven development and the Spec Kit framework, study test-driven development principles as guardrails for agent-written code, review the current state of the art in models and their expected capabilities over the coming year, and use Git to collaborate effectively between people and agents.
The course culminates in each student building a working project that solves a real problem uncovered through their own user understanding. By the end of the module, students are expected to work confidently with Python for data manipulation, collaborate with AI agents using disciplined modern engineering practices, and ship a small product from analysis to prototype.
Learning highlights
- In-depth Python data-manipulation skills with pandas and NumPy
- Precise data science using user-behaviour data and audience analysis, translated into user understanding
- AI-assisted development using spec-driven and Spec Kit workflows
- Test-driven development principles as guardrails for agent-generated code
- Collaborating effectively between people and AI agents using Git
- Understanding current state-of-the-art models and their near-term capabilities
- Placing user understanding at the centre of product building — from analysis to a shipped project
Course outline
15 classes
Session 1
Setup and tooling. Jupyter.
Colab ecosystem and its limits, virtual environments and pip as the baseline (uv and ruff as modern references), git and ssh basics, gdrive integration, AI code completion in the editor.
Session 2
Python for data. Memory, functions, decorators, and generators. Introduction to pandas: reading .csv files and taking a first hands-on look at user-behaviour arrays (event logs) and audience attributes.
Session 3
Data visualisation. Hands on visualisation, automated data visualisation and interactive plotting.
Session 4
NumPy in depth. Arrays, vectorisation, broadcasting, and numerical methods. Using numpy for fast, efficient feature extraction from behavioural arrays.
Session 5
User understanding from behaviour and audience analysis. Exploratory analysis, audience segmentation (cohorts, RFM, data-backed personas), funnels and retention, and visualization - turning behavioural arrays into a precise picture of who the users are and where they struggle: the problem statement that centres the product. Homework checkpoint on sessions 1-4.
Session 6
AI-assisted development: spec-driven development. Writing requirements and acceptance criteria before code, with the spec-kit framework as our working tool. The specification as the shared source of truth for humans and agents; project conventions in the repo (README / AGENTS.md).
Session 7
Test-driven development with agents. TDD principles as guardrails: writing pytest tests first, letting agents implement against red/green feedback, and "verify, don’t trust" - running tests, linters, and type checks over agent-written code.
Session 8
Collaborating between people and agents with Git. Branch-per-task workflows, worktrees for parallel agents, small reviewable increments, clear commit messages, and human review gates before merge.
Session 9
State of the art and what’s next. A brief survey of current models by category (reasoning, long-context, agentic, open-weight), how to read benchmarks critically, and expected capabilities over the following year. Planning before execution, task decomposition, and guardrails for growing autonomy.
Session 10
From user understanding to product. Turning the user understanding and the problem discovered in your analysis into a spec, then generating a project with agents to solve it. Observability and documentation as shared media. Homework checkpoint.
Session 11
Project build sprint. Implementing the solution collaboratively with agents - iterating against specs and tests while keeping every change small and reviewable.
Session 12
Integration via Python. Chatbots, interface prototyping, data annotation, scraping, and no-code platforms - connecting the project to real inputs and outputs.
Session 13
Scaling and performance. Profile first, vectorise before parallelising, chunked processing and Parquet; Polars / DuckDB as references for larger data where the project demands it.
Session 14
Project finishing workshop. Hands-on session to complete, test, document and polish student projects ahead of the final demonstration.
Session 15
Finals. Final exam and student project demonstration.
Course materials
Media
Prerequisites
Knowledge of Python on the level of snakify.org is highly recommended.
A general interest in statistics and data analysis is also a plus.
Methodology
We will study a set of practical Jupyter notebooks, interspersed with relatively short theoretical sections. The first half is focused on hands-on data manipulation and audience analysis aimed at developing user understanding; the second half is project-oriented, with students building software together with AI agents around that understanding.
There will be two substantial homework assignments on data manipulation, designed to emulate a real analytical workflow. Students will develop a personal project that turns their analysis into a working solution using AI-assisted techniques, providing a practical exercise in time management and end-to-end delivery. Finally, students will complete a final exam and give a project demonstration at the end of the course.
Grading
Maxim Musin comes from a background in statistics, advanced multidimensional probability, and random processes. During his career in these fields, he found himself developing skills and gathering experience through working in both academic environments and the private sector. For the last 5 years Maxim is a CEO of for profit AI development laboratory rebels.ai, integrating AI in enterprise and helping startups reach the orbit.
His academic experience ranges from teaching probability and statistics at MSU and MIPT, as a member of the faculty of innovation and high technology, FIHT, which at the time was among the few places worldwide with capabilities for advanced statistics study. During his time there, he produced several notable projects with his students, particularly in regards to the stochastic convergence of neural networks. His course on applied modern statistics became mandatory for the data analysis division of the FIHT MIPT Masters.
See full profileApply for this course
Python the Generative Way: From Data to Product
by Maxim Musin
Total hours
45 Hours
Dates
Oct 19 - Nov 06, 2026
Fee for single course
€1500
Fee for degree students
€750
How to secure your spot
Complete the form below to kickstart your application
Schedule your Harbour.Space interview
If successful, get ready to join us on campus
FAQ
Will I receive a certificate after completion?
Yes. Upon completion of the course, you will receive a certificate signed by the director of the program your course belonged to.
Do I need a visa?
This depends on your case. Please check with the Spanish or Thai consulate in your country of residence about visa requirements. We will do our part to provide you with the necessary documents, such as the Certificate of Enrollment.
Can I get a discount?
Yes. The easiest way to enroll in a course at a discounted price is to register for multiple courses. Registering for multiple courses will reduce the cost per individual course. Please ask the Admissions Office for more information about the other kinds of discounts we offer and what you can do to receive one.