Training course · OpenAI Codex · Data Science & Machine Learning

OpenAI Codex for Data Scientists and ML Engineers

Delegate development work with OpenAI Codex: CLI and cloud agent, AGENTS.md, sandboxing, approvals and team PR workflows.

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

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

OpenAI Codex is a coding agent that runs both locally, as a command-line tool and IDE extension, and as a cloud agent. Locally, Codex reads your repository, proposes changes and runs commands inside a sandboxed environment. In the cloud, it works on delegated tasks in parallel inside isolated containers and returns results as traceable diffs or pull requests. Over two days you will learn how to combine both modes effectively and how to scope tasks so that the agent can complete them reliably and with minimal back-and-forth.

Control and security sit at the heart of the course. With AGENTS.md you hand Codex project knowledge, build and test commands, and conventions. You configure approval modes and sandboxing so that the agent only does what you permit, and you set up cloud environments with suitable setup scripts. You will also integrate Codex into your pull request workflows, use automated code review, and define team rules on which tasks are delegated and how results are checked before they are merged into the main branch.

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 Codex locally and in the cloud for the development tasks each mode suits best.
  • You write an AGENTS.md that guides the agent reliably through your project.
  • You configure approval modes and sandboxing to match your security requirements.
  • You delegate tasks to the cloud agent and review the results systematically.
  • 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 Codex at a glance: CLI, IDE and cloud
  • Comparing how Codex works locally and in the cloud
  • Installing the Codex CLI, signing in and starting it in a repository
  • Interactive sessions, non-interactive execution and model choice
  • Distinguishing tasks that suit a coding agent from those that do not
Module 2 Project knowledge with AGENTS.md
  • Building an AGENTS.md with build, test and lint commands
  • Stating conventions, architectural notes and prohibitions precisely
  • Using nested AGENTS.md files for monorepos and sub-projects
  • Checking effectiveness and refining instructions iteratively
Module 3 Sandboxing, approvals and security
  • Choosing approval modes deliberately, from read-only to largely autonomous
  • Understanding sandbox boundaries for file system and network access
  • Handling secrets, dependencies from the internet and prompt injection
  • Configuration files for team standards and safe defaults
Module 4 Delegating tasks to the cloud agent
  • Configuring cloud environments with setup scripts and dependencies
  • Writing tasks with a clear goal, context and acceptance criteria
  • Launching several tasks in parallel and comparing the results
  • Using logs and test output to understand the proposed solutions

Day 2

Module 5 PR workflows and code review in the team
  • Turning results into pull requests and requesting follow-up changes
  • Using automated Codex code review on GitHub
  • Embedding Codex in scripts and CI pipelines
  • Setting team rules for delegation, review duties and accountability
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, are comfortable with Git and the command line, and know pull-request-based workflows. 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 a terminal, Git and a Node.js runtime; a ChatGPT plan with Codex access or an OpenAI API key, plus a GitHub account for the cloud 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 Bremen Request
  • Mon, 11 January 2027 – Tue, 12 January 2027 Online Request
  • Mon, 25 January 2027 – Tue, 26 January 2027 Salzburg Request
  • Wed, 3 February 2027 – Thu, 4 February 2027 Online Request
  • Tue, 16 February 2027 – Wed, 17 February 2027 Kaiserslautern Request

Frequently asked questions

When should I use Codex locally and when in the cloud?

Locally you work interactively and close to the code, for example when debugging or making exploratory changes where you want to follow every step. The cloud agent suits well-defined tasks that can run independently, such as adding tests or fixing smaller bugs. You can start several of these in parallel and review each one as a pull request.

What belongs in a good AGENTS.md?

A good AGENTS.md explains how the project is built, tested and checked, which conventions apply and which areas must not be touched. It is concise, concrete and kept up to date. Notes on architecture and common pitfalls also help. During the course you write an AGENTS.md for a project of your own and test how it changes the agent’s behaviour.

How safe is it to let Codex run commands?

By default Codex works inside a sandbox with restricted file and network access and asks for approval before risky steps. You decide how much autonomy to grant through approval modes and configuration. In the course you learn to choose these settings deliberately and to limit risks such as prompt injection or running unfamiliar dependencies.

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 “OpenAI Codex 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 OpenAI Codex courses

All 32 OpenAI Codex courses

OpenAI Codex · MunichOpenAI Codex · SalzburgOpenAI Codex · BerlinOpenAI Codex · AugsburgOpenAI Codex · HanoverOpenAI Codex · BremenOpenAI Codex · StuttgartOpenAI Codex · KaiserslauternOpenAI Codex · Online