Training course · Claude Code · Data Science & Machine Learning

Claude Code for Data Scientists and ML Engineers

Agentic coding with Claude Code in the terminal and IDE: CLAUDE.md, subagents, hooks, MCP, CI pipelines and secure permissions.

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

This course connects Claude Code with the everyday processes of Data Science & Machine Learning. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

Claude Code is Anthropic’s agentic coding assistant, working directly in your terminal and in popular IDEs. Rather than completing individual lines, it reads your repository, plans changes across multiple files, runs commands, executes tests and prepares commits. Over two days you will learn to use it with deliberate control: clear project instructions in CLAUDE.md, careful context management, and a workflow in which you set the direction as a developer and can trace every change the agent makes back to a clear intention.

The course is built around real engineering work: diagnosing bugs, delivering features, refactoring legacy code and filling gaps in test coverage. You will configure subagents for specialised tasks, enforce quality checks with hooks, connect external systems through the Model Context Protocol (MCP) and capture team knowledge as reusable skills. Finally, you will run Claude Code headless in CI pipelines and define permissions, sandboxing and approval rules so that its use remains defensible even in security-sensitive environments.

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 Claude Code for multi-step development tasks while keeping full control over every change.
  • You maintain a CLAUDE.md that effectively conveys project conventions, commands and architectural guidance to the agent.
  • You extend Claude Code with subagents, hooks, MCP servers and skills tailored to your team.
  • You integrate Claude Code into Git workflows and CI pipelines with traceable, test-backed 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 How Claude Code works
  • Installation, sign-in and use in the terminal, VS Code and JetBrains IDEs
  • Understanding the agentic loop: read, plan, act, verify
  • Using plan mode to agree on an approach before any code changes
  • Writing effective task briefs with goal, context and acceptance criteria
Module 2 Project context with CLAUDE.md and context management
  • Structuring CLAUDE.md at project, directory and user level
  • Documenting build, test and style conventions so the agent follows them reliably
  • Managing the context window with targeted file references, compaction and fresh sessions
  • Resuming sessions and breaking long tasks into manageable stages
Module 3 Extending Claude Code with subagents, hooks, MCP and skills
  • Defining subagents for code review, research or test generation
  • Using hooks to enforce formatting, linting or checks before and after tool calls
  • Connecting MCP servers for issue trackers, databases or internal documentation
  • Creating custom slash commands and skills for recurring team workflows
Module 4 Git workflows, testing and quality assurance
  • Creating branches, meaningful commits and pull requests with Claude Code
  • Test-first work: have tests written before the implementation
  • Reviewing diffs systematically and rejecting or refining changes
  • Organising parallel work with Git worktrees and multiple sessions

Day 2

Module 5 Headless operation, CI and security
  • Running Claude Code non-interactively in scripts and CI pipelines
  • Automated reviews and issue handling in GitHub or GitLab workflows
  • Configuring permission modes, allow and deny rules, and sandboxing
  • Handling secrets, prompt injection risks and organisation-wide policies
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 have hands-on programming experience in at least one language and are comfortable with Git and the command line. 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 admin rights, Git, a Node.js runtime and an up-to-date editor; a Claude subscription or Anthropic API access is required for the exercises.

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.

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Thu, 10 December 2026 – Fri, 11 December 2026 Salzburg Request
  • Wed, 16 December 2026 – Thu, 17 December 2026 Online Request
  • Thu, 21 January 2027 – Fri, 22 January 2027 Bremen Request
  • Mon, 25 January 2027 – Tue, 26 January 2027 Online Request
  • Thu, 4 February 2027 – Fri, 5 February 2027 Augsburg Request

Frequently asked questions

How is Claude Code different from traditional code completion?

Code completion suggests the next few lines, whereas Claude Code acts as an agent that handles whole tasks: it searches the repository, plans changes across several files, runs tests and commands, and corrects itself based on the results. You define the goal and review the outcome instead of steering every single line yourself.

Is Claude Code secure enough for enterprise use?

By default, Claude Code asks for approval before editing files or running commands. Permission rules, sandboxing, managed settings and hooks let you define precisely what the agent may do. During the course you learn to configure these mechanisms to match your security and data protection requirements and to assess risks such as prompt injection.

Does Claude Code work with my language and tech stack?

Yes. Claude Code is language-agnostic because it works with files, terminal commands and your existing build and test tooling. Whether you use Python, Java, TypeScript, Go, SAP-related code or infrastructure as code, what matters most is a well-written CLAUDE.md describing your commands and conventions. Each course variant adds the relevant domain focus.

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 “Claude Code 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 Claude Code courses

All 77 Claude Code courses

Claude Code · MunichClaude Code · SalzburgClaude Code · BerlinClaude Code · AugsburgClaude Code · HanoverClaude Code · BremenClaude Code · StuttgartClaude Code · KaiserslauternClaude Code · Online