Training course · OpenAI Codex · UX Design & Prototyping

OpenAI Codex for UX Designers

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

This course connects OpenAI Codex with the everyday processes of UX Design & Prototyping. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

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.

AI coding tools are shifting the boundary between design and development: UX designers can now build interactive prototypes in real code instead of only drawing clickable mock-ups. A screenshot, a sketch or a short description quickly becomes a working interface with real states, form logic and sample data that feels like a finished product in usability testing. AI assistants also translate design tokens, component libraries and accessibility checks straight into code. In this course you learn how vibe coding and AI agents take you from idea to testable prototype faster, how to hand results over cleanly to engineering teams and where the line runs between a prototype and production-ready software.

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?

  • UX and UI designers
  • Product designers and interaction designers
  • UX researchers who want to test variants quickly
  • Product owners and product managers with design responsibility
  • Design system teams working closely with frontend engineering

Typical challenges we address

  • Static mock-ups barely capture interactions, states and real data
  • Hand-offs to engineering lose details, spacing and behavioural logic
  • Long waits for engineering capacity to run experiments and A/B variants
  • Accessibility is often considered late and incompletely

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.
  • Build interactive, code-based prototypes with AI and test ideas with users much earlier.
  • Translate design systems and tokens into code and improve hand-offs to engineering teams.
  • Review prototypes systematically for accessibility and understand the line between prototype and production code.

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: UX Design & Prototyping
  • Clickable prototypes in code
  • Generating test variants
  • Turning design tokens into code
  • Checking accessibility
  • Designing microinteractions
  • Synthesising research
Module 7 Data protection, quality & transfer to daily work
  • Prototypes often contain unreleased product ideas and research data from participants: you learn to pseudonymise interview notes in line with the GDPR, clarify rights to fonts, images and generated assets and plan early for the European Accessibility Act.
  • 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

Clickable prototypes in code

Turn sketches, wireframes or screenshots into working web prototypes with navigation, form validation, loading and error states and realistic sample data that can be tested directly in the browser.

Generating test variants

Produce several design variants of a flow in parallel, for example onboarding or checkout, and prepare them for usability tests or A/B experiments with minimal adjustments.

Turning design tokens into code

Structure colours, typography, spacing and radii from your design system as tokens and convert them into CSS variables, Tailwind configuration or theme files for component libraries.

Checking accessibility

Examine prototypes for contrast, semantic HTML, keyboard navigation, focus order and ARIA attributes and have concrete WCAG-based improvements applied directly in the code. Issues are fixed before reaching engineering.

Designing microinteractions

Describe transitions, animations and feedback states and implement them in CSS or JavaScript, so you can judge timing and effect early in the real medium rather than in a drawing tool.

Synthesising research

Cluster notes from interviews and usability tests, surface patterns and pain points and derive prioritised design hypotheses that feed straight into the next prototype iteration.

Possible hands-on projects

Onboarding prototype

A multi-step onboarding flow as a web app with a progress indicator, validation and saved inputs, ready for moderated usability testing.

Token converter

A small tool that reads exported design tokens and generates CSS variables, a colour palette with contrast ratios and a preview page.

Component playground

An overview page showing your design system’s buttons, forms and cards in every state, including light and dark mode. It doubles as a living reference.

Prerequisites

You have hands-on programming experience, are comfortable with Git and the command line, and know pull-request-based workflows. You have experience in UX or UI design and with common design tools; no programming skills are required, although a basic understanding of HTML and CSS helps.

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

Prototypes often contain unreleased product ideas and research data from participants: you learn to pseudonymise interview notes in line with the GDPR, clarify rights to fonts, images and generated assets and plan early for the European Accessibility Act.

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
  • Wed, 13 January 2027 – Thu, 14 January 2027 Online Request
  • Mon, 18 January 2027 – Tue, 19 January 2027 Berlin Request
  • Wed, 27 January 2027 – Thu, 28 January 2027 Online Request
  • Thu, 11 February 2027 – Fri, 12 February 2027 Munich 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.

Do I need to know how to code as a designer?

No. You describe interfaces and behaviour in plain language, with sketches or screenshots, and the AI tool generates the code. It helps to understand basic terms such as component, state or CSS class so you can steer precisely. We cover these concepts hands-on in the course, so you can adapt and evolve prototypes on your own.

Can the engineering team reuse the prototype code?

Sometimes, but more often it serves as a precise specification. Prototypes are optimised for speed, not for security, performance or maintainability. If you use the same component library and tokens as the product from the outset, reuse becomes much more likely. In the course you work out how to design hand-offs that benefit both sides.

How much does “OpenAI Codex for UX Designers” 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 UX Designers

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