Training course · Agentic Coding · Data Science & Machine Learning

Agentic Coding for Data Scientists and ML Engineers

Use autonomous coding agents effectively: specs instead of prompts, task decomposition, test-driven loops, multi-agent setups and governance.

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

“Agentic Coding 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 Agentic Coding in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from Data Science & Machine Learning.

Agentic coding means working with AI agents that carry out development tasks largely on their own: they read code, plan changes, run commands and tests, and correct themselves based on the results. Tools such as Claude Code, OpenAI Codex, the GitHub Copilot coding agent and Cursor’s agent mode have made this way of working practical for everyday use. This vendor-neutral course teaches the underlying methodology so that you achieve reliable results whatever the tool, and redefine the developer’s role within your engineering team.

The core shift is from ad hoc prompts to robust specifications. You will learn to decompose and describe tasks so that agents solve them reliably, to set up test-driven loops in which tests act as objective acceptance criteria, and to run several agents in parallel or with a division of labour. We also cover review strategies for agent-generated code and team governance: permissions, security boundaries, accountability, cost control and the gradual introduction of agentic workflows into your existing development 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 understand how coding agents work and choose the right tool and level of autonomy.
  • You write specifications and project context that agents can work with reliably.
  • You break initiatives into verifiable sub-tasks and steer agents through test-driven loops.
  • You use multi-agent setups and parallel work in a controlled way.
  • 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 Foundations of agentic development
  • How coding agents work: tool calls, context windows and feedback loops
  • Comparing tools: terminal agents, IDE agents and cloud agents
  • Recognising suitable tasks and choosing levels of autonomy deliberately
  • The new role in the team: from implementation to steering and acceptance
Module 2 Specifications instead of prompts
  • Describing tasks with goal, context, constraints and acceptance criteria
  • Keeping project context in files such as CLAUDE.md, AGENTS.md or rules
  • Plan-first approach: let the agent draft a solution and review it before implementation
  • Versioning specifications and maintaining them as part of the repository
Module 3 Task decomposition and test-driven agent loops
  • Breaking large initiatives into independent, verifiable sub-tasks
  • Having tests written first and using them as an objective stopping criterion
  • Using linters, type checks and builds as automatic feedback
  • Recognising stuck loops and restarting with a new strategy
Module 4 Multi-agent setups and parallel work
  • Defining specialised subagents for research, implementation, testing and review
  • Organising parallel work with branches, worktrees and isolated environments
  • Orchestration: merging results and resolving conflicts
  • Sharing tools and data sources through MCP

Day 2

Module 5 Review, security and team governance
  • Review strategies for large, agent-generated changes
  • Defining permissions, sandboxing and protection against prompt injection
  • Embedding agents in CI pipelines and pull request processes
  • Planning team guidelines, accountability, costs and a phased rollout
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 several years of development experience, are confident with Git, testing and CI, and ideally have already used AI coding tools. 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 Git, a terminal and your development environment, plus access to at least one coding agent such as Claude Code, Codex, Copilot or Cursor.

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
  • Wed, 9 December 2026 – Thu, 10 December 2026 Stuttgart Request
  • Thu, 7 January 2027 – Fri, 8 January 2027 Hanover Request
  • Mon, 11 January 2027 – Tue, 12 January 2027 Online Request
  • Wed, 20 January 2027 – Thu, 21 January 2027 Berlin Request
  • Tue, 2 February 2027 – Wed, 3 February 2027 Online Request

Frequently asked questions

How does agentic coding differ from vibe coding?

Vibe coding relies on fast, intuitive iteration in natural language and is particularly suited to prototypes. Agentic coding is an engineering discipline for professional codebases: precise specifications, tests as acceptance criteria, clear permissions and structured reviews ensure that agents deliver reliable, maintainable results even in complex, long-lived projects.

Is the course tied to a specific tool?

No. The course teaches methods that work with Claude Code, OpenAI Codex, the GitHub Copilot coding agent, Cursor and comparable tools. The exercises highlight differences and common ground, for example in context files, permissions and subagents. You can work with whichever tool your organisation already uses or plans to adopt.

How do we stay in control of quality and security with autonomous agents?

Control comes from several layers: tightly scoped permissions and sandboxing, tests and static analysis as automatic checks, mandatory human review before merging, and clear team rules on accountability. During the course you develop a governance concept that fits your processes, security requirements and regulatory obligations.

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 “Agentic Coding 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 Agentic Coding courses

All 32 Agentic Coding courses

Agentic Coding · MunichAgentic Coding · SalzburgAgentic Coding · BerlinAgentic Coding · AugsburgAgentic Coding · HanoverAgentic Coding · BremenAgentic Coding · StuttgartAgentic Coding · KaiserslauternAgentic Coding · Online