Course · Training · Workshop
Codex for Enterprise Engineering
Two days hands-on with OpenAI Codex: build, test and review features on existing projects in CLI, IDE, ChatGPT desktop app and cloud, safely with sandbox, approvals and AGENTS.md.
This specialized course introduces professional software development with OpenAI Codex, OpenAI's coding agent for terminal, IDE, ChatGPT desktop app and cloud. Participants learn how to integrate Codex as an active peer programmer into their development workflow, where the agent directly reads, modifies, tests, builds and executes code. The course covers Codex-specific strategies such as project context via AGENTS.md, how sandbox and approval policy work together, cloud environments for parallel tasks, code reviews with @codex on pull requests, and extending Codex through skills, hooks, plugins and MCP servers. Participants will work with existing software projects including single page application frontends, REST backends, databases and API integrations. The course focuses on fixing issues, debugging, implementing new features, understanding code and building a Codex-specific agentic workflow context framework. Participants build their own small MCP server and run Codex headless with codex exec and the Codex SDK in a pipeline. There will be an overview of ChatGPT Business and Enterprise, usage via OpenAI API keys, and centrally managed configuration with requirements.toml for the enterprise rollout. The course primarily focuses on the Codex CLI, IDE extension, ChatGPT desktop app and Codex Cloud, but also covers alternative integrations and deployment scenarios for enterprises.
What participants say
The “AI Assisted Engineering On-Boarding” course was an outstanding experience. It provided a clear, practical, and inspiring introduction to how AI can support modern engineering work. The content was well structured, easy to follow, and highly relevant to real day-to-day challenges. What stood out most was the strong balance between theory and hands-on application. The course not only explained the concepts clearly, but also showed how to use AI tools effectively and responsibly in actual engineering scenarios. It made complex topics feel accessible and immediately useful. I especially appreciated the engaging format, the high quality of the materials, and the clear expertise of the instructors. The course created a motivating learning environment and gave me valuable confidence in applying AI-assisted approaches in my work. Overall, I can highly recommend “AI Assisted Engineering On-Boarding” to anyone who wants a practical, forward-looking, and well-designed introduction to AI in engineering. It is an excellent course that delivers real value from start to finish.
Leiter IT Entwicklung Platform & Services
The AI Assisted Engineering On-Boarding course was very practical and easy to follow and awesome! I especially appreciated the hands-on approach and the focus on real use cases. It gave me a clear understanding of how to work effectively with Claude Code in a development context. After the course, I felt much more confident getting started and applying it in daily work.
Frontend Web Developer
The Agentic Product Engineering course gave me a completely new perspective on modern product development with AI agents. From the fundamentals to advanced workflows, everything was explained clearly and presented in a way that was easy to understand and apply. The concepts and techniques I learned could be integrated directly into my daily work. I was impressed and engaged from start to finish. Highly recommended for anyone looking to leverage AI agents in product development.
Chief Product Officer
The day was both intense and practical, with a range of exercises and challenges designed to provide valuable insights into agentic AI systems and modern product engineering.
Head Digital Transformation
The course fully met all my expectations and provided a smooth introduction to the subject. With the help of the instructor and the course materials, I was able to easily overcome any initial hurdles, allowing me to get started using the agents as quickly as possible.
Senior Software Engineer
I really enjoyed the lessons and learned a lot of new stuff on this course. It teaches not only fundamentals but also how to be prepared for your next challenges. The tooling that is used is very sturdy, works very well in the lab setup and is very diverse, you can pick what you like in your projects. And most importantly: I did not write any piece of code myself, the agents did everything!
Software Engineer I
* Voices from this or related courses.






These customers booked courses in the same topic cluster.More customers →
Content
The course will consist of the following topics and may be extended or adapted based on the audience. The examples in the course will focus on widely used programming languages, software architectures and frameworks. For in-house courses there is a selection of programming languages and frameworks which can be chosen to better fit the audience.
Introduction to OpenAI Codex for Enterprise Development
- Evolution from autocomplete assistants to coding agents
- The Codex agent loop: model, tools, context
- Overview of Codex CLI, IDE extension, ChatGPT desktop app and Codex Cloud
- Model selection and reasoning effort
Codex Setup and Configuration
- Installing the Codex CLI and the IDE extension
- Sign-in with a ChatGPT account or OpenAI API key
- config.toml: layers, profiles and project-specific configuration
- Hands-On: set up Codex in your own project
Sandbox, Approvals and Security
- Sandbox modes: read-only, workspace-write, danger-full-access
- How the sandbox is enforced on macOS, Linux and Windows
- Approval policy, auto-review and network access
- Command rules for allowed and forbidden commands
- Hands-On: define safe defaults for the team
Context Management with AGENTS.md
- Building effective project contexts for Codex
- Global, repository and directory level, override files
- Defining rules, conventions and build/test commands
- Hands-On: write an AGENTS.md for an existing project
Working with Existing Codebases in Codex
- Strategies for code analysis with Codex
- Code comprehension and automatic documentation generation
- Refactoring and optimization with Codex support
- Handling large codebases and legacy systems
Practical Development Tasks with Codex
- Debugging and problem-solving with the Codex agent
- Feature implementation in existing applications
- Test creation and validation with Codex
- Hands-On: one feature from issue to pull request
Frontend and Backend Development with Codex
- Single page application development and component generation
- Visual checks in the browser and end-to-end testing
- REST API design, database integration and schema design
- Performance optimization and monitoring
Codex Cloud and Parallel Agents
- Delegating tasks to cloud agents
- Cloud environments: setup script, secrets and internet access
- Parallel tasks, worktrees and subagents
- Comparing results and taking them over as a pull request
Code Review with Codex
- Reviews with @codex review on pull requests
- Automatic reviews for a repository
- Team review rules in AGENTS.md
- Hands-On: Codex as reviewer in your own repository
Codex Headless and in CI/CD
- codex exec for non-interactive tasks
- Structured output with JSON Lines and output schema
- Codex in GitHub Actions and other pipelines
- Codex SDK for TypeScript and Python
- Hands-On: use Codex in a pipeline
MCP Servers for Codex
- Understanding the Model Context Protocol
- Configuring MCP servers in Codex: STDIO, HTTP and OAuth
- Implementing your own MCP server
- Hands-On: connect Codex to an internal service
Skills, Hooks and Plugins
- Skills as reusable instructions and workflows
- Hooks for checks before and after tool calls
- Plugins and marketplaces for distribution in the team
- Hands-On: build your own skill for team conventions
Enterprise Rollout of Codex
- ChatGPT Business vs. Enterprise vs. API usage
- Admin controls for local and cloud use, RBAC and audit logs
- Centrally managed configuration with requirements.toml
- Usage limits, credits and cost control
Enterprise Codex Framework
- Building reusable Codex workflows
- Team collaboration and knowledge sharing
- Security policies and compliance management
- Integration into existing DevOps pipelines
The course primarily focuses on OpenAI Codex with the Codex CLI, IDE extension, ChatGPT desktop app and Codex Cloud. Alternative integrations and deployment scenarios are discussed to provide a comprehensive enterprise perspective. The concepts and workflows taught are specifically optimized for Codex but can serve as a foundation for other agentic coding tools.
The actual course content may differ from the above depending on the trainer, delivery, duration and the composition of participants.
Request this course in-house
Request a public date
No suitable public date? Register without obligation — once there is enough interest we schedule a new public date and let you know first.
More about OpenAI Codex
Codex is OpenAI's coding agent. It runs locally as the Codex CLI in the terminal, as an IDE extension for VS Code, Cursor and Windsurf and in the Codex mode of the ChatGPT desktop app, or in the cloud, where it works on tasks in parallel in their own VMs and proposes pull requests. Codex gets project knowledge from AGENTS.md files. The sandbox defines what is technically possible, the approval policy when Codex asks. Skills, hooks, plugins and MCP servers extend Codex, and with requirements.toml admins set rules that nobody can override locally.Further resources:
History
The name Codex comes from an early code model by OpenAI that powered the first GitHub Copilot in 2021. In spring 2025 OpenAI reused the name for a new generation: first the open source Codex CLI for the terminal, then in May 2025 Codex as a cloud agent in ChatGPT that implements tasks on its own in isolated environments. In October 2025 Codex became generally available, with Slack integration, SDK and admin tools.
2026 brought the Codex app for macOS and Windows, which merged into the ChatGPT desktop app in July 2026, as well as hooks, plugins, subagents and centrally managed configuration for enterprises. Alongside Claude Code and GitHub Copilot, Codex is now one of the key tools for agentic software engineering.

