Training course · Windsurf · Data Science & Machine Learning

Windsurf for Data Scientists and ML Engineers

Develop with the Windsurf AI IDE and its Cascade agent: flows, memories, rules, workflows and safe use across the team.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

“Windsurf for Data Scientists and ML Engineers” is designed for roles such as Data scientists in business units and analytics teams, ML engineers responsible for training and deployment and Data analysts moving into Python and machine learning and shows step by step how to use Windsurf productively, safely and transparently in Data Science & Machine Learning – from the fundamentals to advanced workflows.

Windsurf is an AI-powered development environment built around its agent, Cascade. Cascade understands the structure of your project, follows your actions in the editor and terminal, and works with you according to the flow principle: you and the agent take turns on the same task without having to re-explain context over and over. In this two-day course you will learn how to use Cascade effectively for features, debugging and refactoring, and how to make the most of intelligent completion in your daily development work.

To keep results consistent across a team, you steer Cascade with global and workspace rules, rely on memories for lasting project knowledge and automate recurring procedures with workflows that run from a slash command. You will connect external tools through MCP, control how terminal commands are executed and decide which data Cascade is allowed to see. Finally, you will define rules for code review, security and data protection so that Windsurf can be used responsibly within your organisation and its existing processes.

Data science and machine learning thrive on moving quickly between exploration, modelling and production. A great deal of time goes into data preparation with pandas or Polars, feature engineering, visualisation, hyperparameter experiments and finally turning notebook code into maintainable pipelines. AI coding assistants and agents speed up every one of these steps: they write exploration and plotting code, suggest validation strategies, refactor notebooks into tested Python modules, build scikit-learn or PyTorch training scripts and set up experiment tracking with MLflow. Methodological rigour is essential, though, because plausible-looking code can hide data leakage or misleading metrics. This course teaches you to use AI productively while safeguarding the statistical quality of your results.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Data scientists in business units and analytics teams
  • ML engineers responsible for training and deployment
  • Data analysts moving into Python and machine learning
  • Researchers and developers with notebook-heavy workflows
  • MLOps teams running models in production

Typical challenges we address

  • Messy notebooks that are hard to reproduce and put into production
  • Time-consuming data preparation and feature engineering
  • Methodological pitfalls such as data leakage, unsuitable metrics or flawed validation
  • Lack of traceability for experiments, models and data versions

What you will be able to do

  • You use Cascade productively in flow for features, debugging and refactoring.
  • You steer Windsurf’s context precisely and keep sensitive content protected.
  • You maintain memories and rules that reliably enforce your project conventions.
  • You automate recurring procedures with workflows and connect external tools via MCP.
  • Accelerate exploration, feature engineering and modelling with AI assistants without sacrificing methodological rigour.
  • Use AI agents to turn notebook code into tested, reproducible ML pipelines.
  • Recognise typical errors in generated ML code, such as data leakage or unsuitable metrics, and correct them deliberately.

Course outline

Day 1

Module 1 Getting to know Windsurf and Cascade
  • Installation, importing existing editor settings and basic configuration
  • Cascade in code and chat mode: when the agent edits and when it only advises
  • The flow principle: how Cascade takes your editor and terminal actions into account
  • Intelligent completion and inline commands in everyday development
Module 2 Steering context
  • Understanding codebase indexing and referencing relevant files or directories
  • Bringing documentation, web sources and terminal output into context
  • Excluding sensitive content from context with ignore files
  • Structuring sessions and starting afresh when the topic changes
Module 3 Memories and rules for consistent results
  • Reviewing and maintaining auto-generated and manually created memories
  • Creating and versioning global and workspace rules
  • Expressing architecture, style and testing guidelines as effective rules
  • Activating rules selectively by file pattern or occasion
Module 4 Workflows and automation
  • Defining recurring procedures as workflows and launching them via slash command
  • Building workflows for release preparation, testing or code maintenance
  • Connecting MCP servers for issue trackers, databases or internal services
  • Controlling terminal command execution with allow and deny lists

Day 2

Module 5 Quality, review and governance
  • Tracing Cascade’s changes, accepting them partially or reverting them
  • Using a test-driven approach and preview features for verification
  • Team settings, data protection options and handling of secrets
  • Defining review processes and accountability for AI-generated code
Module 6 Practice lab: Data Science & Machine Learning
  • Exploratory data analysis
  • Turning notebooks into pipelines
  • Model training and validation
  • Experiment tracking and MLOps
  • Explaining and auditing models
  • Evaluating LLM and RAG prototypes
Module 7 Data protection, quality & transfer to daily work
  • Training and analysis data often contains personal information, so use schemas, aggregates or synthetic data in prompts and observe GDPR principles such as purpose limitation. For high-risk applications, the EU AI Act sets requirements on data quality, documentation and transparency, and the licences of datasets, pre-trained models and Python packages must also be checked.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Exploratory data analysis

The assistant writes code for data profiles, distributions, correlations and missing values with pandas or Polars, produces meaningful visualisations and summarises anomalies as hypotheses for modelling.

Turning notebooks into pipelines

The agent refactors notebook code into Python modules with functions, configuration and pytest tests, removes hidden state and makes training and inference reproducible. Results become reliably comparable.

Model training and validation

The AI builds scikit-learn pipelines or PyTorch training loops with proper cross-validation, suitable metrics and baselines, and actively flags risks such as data leakage or class imbalance.

Experiment tracking and MLOps

The assistant sets up MLflow or similar tools for parameters, metrics and artefacts, versions models and creates training and deployment workflows for the CI/CD pipeline.

Explaining and auditing models

Using SHAP, permutation importance or partial dependence plots, the AI produces explanations of model decisions as well as analyses of fairness and robustness across relevant subgroups.

Evaluating LLM and RAG prototypes

The AI helps build evaluation datasets, automated scoring metrics and comparison experiments for prompt variants, embedding models or retrieval strategies. Quality, cost and latency of variants can be compared objectively.

Possible hands-on projects

Churn prediction with explanations

A complete project from data preparation through a gradient boosting model to a small Streamlit app displaying predictions and SHAP explanations.

Model monitoring script

A script that compares data and prediction distributions over time, detects drift and produces a compact report with charts. The team is notified automatically when anomalies appear.

Evaluation harness for a RAG chatbot

A test set-up with a question set, reference answers and automated scoring that compares different retrieval and prompt configurations. Results are summarised per configuration in a clear table.

Prerequisites

You program regularly in at least one language and are familiar with Git and a modern IDE. Good Python skills, experience with pandas or Polars and scikit-learn, and a grounding in statistics and machine learning.

Technical requirements

Your own laptop with the Windsurf editor, Git and your usual toolchain installed; a Windsurf account with access to Cascade is required.

Data protection & compliance

Training and analysis data often contains personal information, so use schemas, aggregates or synthetic data in prompts and observe GDPR principles such as purpose limitation. For high-risk applications, the EU AI Act sets requirements on data quality, documentation and transparency, and the licences of datasets, pre-trained models and Python packages must also be checked.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Thu, 26 November 2026 – Fri, 27 November 2026 Online Request
  • Tue, 8 December 2026 – Wed, 9 December 2026 Berlin Request
  • Wed, 16 December 2026 – Thu, 17 December 2026 Online Request
  • Tue, 12 January 2027 – Wed, 13 January 2027 Online Request
  • Tue, 19 January 2027 – Wed, 20 January 2027 Hanover Request
  • Thu, 4 February 2027 – Fri, 5 February 2027 Online Request

Frequently asked questions

What does Windsurf mean by flows?

Flows describe the close collaboration between you and Cascade. The agent observes what you do in the editor and terminal and takes those actions into account in its next steps. As a result you do not have to keep explaining where you are, and you can move smoothly between doing the work yourself and delegating it to the agent.

How do memories, rules and workflows differ?

Memories store knowledge that Cascade has gathered while working or that you have explicitly recorded. Rules are guidelines you write that shape the agent’s behaviour permanently. Workflows are reusable sequences of steps for recurring tasks, launched with a slash command. Together they keep results consistent across the whole team.

Can I use Windsurf with my existing projects and languages?

Yes. Windsurf is language-agnostic and works with your existing toolchain, including build tools, package managers and test frameworks. Whether you work on back end, front end, data processing or infrastructure code, what matters is giving Cascade good rules and clear context. Each course variant adds the specific focus for your field.

Can I trust AI on statistical questions?

AI assistants know common methods very well but occasionally make methodological mistakes, for example in splitting training and test data or choosing metrics. On the course you learn to ask the AI explicitly about assumptions and risks, check results against baselines and sanity checks, and keep professional accountability firmly with yourself.

Does AI-assisted coding work in Jupyter notebooks?

Yes. Many assistants support notebooks directly, and agents can also read, execute and convert notebooks into modules. We show when notebooks are ideal for exploration and how to make the transition to versioned, tested code efficiently with AI support. The two approaches complement each other.

How much does “Windsurf for Data Scientists and ML Engineers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Data Scientists and ML Engineers

More Windsurf courses

All 32 Windsurf courses

Windsurf · MunichWindsurf · SalzburgWindsurf · BerlinWindsurf · AugsburgWindsurf · HanoverWindsurf · BremenWindsurf · StuttgartWindsurf · KaiserslauternWindsurf · Online