Training course · Cursor · Data Science & Machine Learning

Cursor for Data Scientists and ML Engineers

Work productively with the AI code editor Cursor: agent mode, rules, codebase context, Tab completion, background agents and review.

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

“Cursor for Data Scientists and ML Engineers” is a hands-on course 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. Rather than learning Cursor in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from Data Science & Machine Learning.

Cursor is an AI code editor built on VS Code that weaves language models deeply into everyday development. Alongside context-aware Tab completion, it offers an agent mode that searches files on its own, plans changes across the whole project, runs terminal commands and fixes errors iteratively. In this two-day course you will learn to use Cursor with purpose: choosing the right interaction mode, steering context deliberately and combining AI assistance with your existing workflow of version control, automated testing and peer code review.

A key focus is making Cursor work for teams. Project rules let you capture architectural decisions, naming conventions and testing strategies so that the agent produces consistent results. You will learn to make good use of codebase indexing, targeted references to files, documentation and symbols, and MCP integrations. You will also delegate tasks to background agents, review their output as pull requests and set up a review process that takes quality, security and data protection seriously across the organisation.

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 choose the right Cursor mode for each task and use it efficiently.
  • You steer codebase context precisely and get more accurate suggestions as a result.
  • You write project rules that reliably enforce your team’s conventions.
  • You use agent mode and background agents for features and refactorings with verifiable results.
  • 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 Setting up Cursor and understanding its modes
  • Installation and migration of VS Code settings and extensions
  • Differences between Tab completion, inline edits, Ask mode and Agent mode
  • Choosing a model per task: balancing speed, depth and cost
  • Privacy mode and organisation-level settings
Module 2 Steering codebase context
  • How codebase indexing works and where its limits lie
  • Referencing files, folders, symbols, documentation and web sources precisely
  • Using ignore files to exclude sensitive or irrelevant content
  • Avoiding overlong chats and restarting tasks with fresh context
Module 3 Rules for consistent team results
  • Creating and versioning project rules and scoping them by file pattern
  • Expressing architecture, style and testing conventions as effective rules
  • Separating user rules from team rules
  • Refining rules iteratively based on the agent’s typical mistakes
Module 4 Agent mode in practice
  • Building features step by step with plan, implementation and tests
  • Running multi-file refactorings safely with checkpoints
  • Approving terminal commands deliberately and feeding error output back
  • Connecting MCP servers for issue trackers, databases or browser testing

Day 2

Module 5 Background agents, review and governance
  • Delegating tasks to background agents and running them in parallel
  • Reviewing results as branches or pull requests and steering follow-ups
  • Using AI-assisted code review alongside human review
  • Addressing security risks, secrets and licensing in enterprise use
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 an IDE such as VS Code. 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 Cursor, Git and your usual development environment installed; a Cursor account with access to agent features is recommended.

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.

  • Tue, 24 November 2026 – Wed, 25 November 2026 Online Request
  • Thu, 3 December 2026 – Fri, 4 December 2026 Hanover Request
  • Mon, 14 December 2026 – Tue, 15 December 2026 Online Request
  • Thu, 7 January 2027 – Fri, 8 January 2027 Online Request
  • Wed, 13 January 2027 – Thu, 14 January 2027 Munich Request
  • Wed, 20 January 2027 – Thu, 21 January 2027 Online Request

Frequently asked questions

Do I need prior VS Code experience to use Cursor?

It helps, but it is not essential. Cursor is built on VS Code, so navigation, shortcuts and extensions feel familiar and existing settings can be imported. If you currently work with JetBrains IDEs or other editors, a short introduction during the course gets you up to speed quickly so you can concentrate on the AI features.

How do I prevent confidential code from reaching third parties?

Cursor offers a privacy mode and organisation settings that restrict how code is stored by the provider. You can also use ignore files to exclude sensitive areas from indexing and context. In the course we discuss how to align these options with internal policies, data protection requirements and sound handling of secrets.

What do rules add compared with well-written prompts?

A prompt applies to one request only, whereas rules persist and apply to the whole team. They capture architectural decisions, preferred libraries, testing strategies and style guidelines, so nobody has to repeat that information and the agent produces code that fits your codebase. Rules are versioned with the project and evolve together with it.

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 “Cursor 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 Cursor courses

All 32 Cursor courses

Cursor · MunichCursor · SalzburgCursor · BerlinCursor · AugsburgCursor · HanoverCursor · BremenCursor · StuttgartCursor · KaiserslauternCursor · Online