Training course · GitHub Copilot · Data Science & Machine Learning

GitHub Copilot for Data Scientists and ML Engineers

Use GitHub Copilot professionally: completions, chat, agent mode, the coding agent for issues and PRs, code review and enterprise policies.

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

“GitHub Copilot 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 GitHub Copilot productively, safely and transparently in Data Science & Machine Learning – from the fundamentals to advanced workflows.

GitHub Copilot has grown from simple code completion into a broad AI platform that supports the entire development lifecycle. In the editor you work with inline suggestions, next edit suggestions and Copilot Chat; in agent mode Copilot handles tasks across multiple files and runs commands. On GitHub itself, the coding agent picks up assigned issues and delivers pull requests. In this two-day course you will learn how to use each of these building blocks deliberately and fit them cleanly into your existing development process.

Beyond hands-on editor work, the course covers control and quality. Custom instructions and prompt files give Copilot the project knowledge it needs, MCP adds further tools, and Copilot code review complements human reviewers. For those responsible for teams and organisations, we look at policies at organisation and enterprise level, content exclusions, model availability and usage reporting. Together, these lay the groundwork for a secure, transparent and genuinely effective Copilot rollout across the entire company.

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 Copilot completions, chat and agent mode purposefully for your everyday development tasks.
  • You capture project knowledge in custom instructions and prompt files to improve output quality.
  • You delegate suitable issues to the coding agent and review its pull requests properly.
  • You integrate Copilot code review sensibly into your existing review process.
  • 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 Copilot in the editor: completions and chat
  • Accepting, rejecting and steering inline and next edit suggestions efficiently
  • Using Copilot Chat for explanations, debugging and test generation
  • Setting context precisely with files, selections, workspace and chat variables
  • Model selection and differences between VS Code, Visual Studio and JetBrains IDEs
Module 2 Agent mode and extensions
  • Planning multi-step tasks in agent mode and executing them under control
  • Feeding terminal commands, test runs and error output into the agent loop
  • Connecting MCP servers for additional tools and data sources
  • Reviewing changes, accepting them partially or rolling them back
Module 3 Project knowledge through custom instructions
  • Writing repository-wide instructions on architecture, style and testing
  • Creating path-specific instructions and reusable prompt files
  • Combining personal and organisation-wide guidance sensibly
  • Refining instructions continuously based on output quality
Module 4 Coding agent and code review on GitHub
  • Writing issues the coding agent can implement reliably
  • Reviewing, commenting on and iterating over the agent’s pull requests
  • Using Copilot code review as an additional check in the PR process
  • Configuring the agent’s development environment with setup steps and Actions

Day 2

Module 5 Administration, policies and security
  • Licence assignment and policies at organisation and enterprise level
  • Content exclusions, model availability and public code filters
  • Using audit logs and usage metrics to steer adoption
  • Clarifying security risks, secrets 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 develop software regularly, work with Git and GitHub issues and pull requests, and use 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 VS Code or a JetBrains IDE, the Copilot extension installed and a GitHub account with an active Copilot licence; the coding agent requires a suitable plan.

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
  • Thu, 14 January 2027 – Fri, 15 January 2027 Online Request
  • Mon, 18 January 2027 – Tue, 19 January 2027 Hanover Request
  • Thu, 28 January 2027 – Fri, 29 January 2027 Online Request

Frequently asked questions

What is the difference between agent mode and the coding agent?

Agent mode runs inside your IDE: you work interactively with Copilot, see every step and approve commands. The coding agent, by contrast, works autonomously on GitHub once you assign it an issue, uses its own execution environment and opens a pull request that you then review just as you would a contribution from a colleague.

How can we make sure Copilot complies with our company policies?

At organisation and enterprise level you can enable or block specific features, models and extensions. Content exclusions keep sensitive files out of the context, and audit logs make usage traceable. During the course we show how to align these controls with data protection, information security requirements and your internal coding standards.

Is the course worthwhile if we already use Copilot?

Yes, especially then. Many teams rely on completions alone and barely touch chat, agent mode, custom instructions or the coding agent. The course shows how to use these features in a structured way, improve results with project knowledge and avoid common pitfalls. Experienced users benefit most from the sections on review and governance.

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 “GitHub Copilot 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 GitHub Copilot courses

All 32 GitHub Copilot courses

GitHub Copilot · MunichGitHub Copilot · SalzburgGitHub Copilot · BerlinGitHub Copilot · AugsburgGitHub Copilot · HanoverGitHub Copilot · BremenGitHub Copilot · StuttgartGitHub Copilot · KaiserslauternGitHub Copilot · Online