OpenAI Shows How Codex Is Being Used in Engineering Workflows
OpenAI says its teams use ChatGPT and Codex across mechanical design, electrical engineering, CAD, and simulation. It describes a Chip Ganassi Racing workflow test and a research collaboration with Mazda, with partner engineers reviewing outputs as the work develops.
OpenAI is describing how ChatGPT and Codex are being used in practical engineering work, from CAD and electronics to simulation. The company’s overview covers internal hardware work and early industry collaborations, rather than announcing a public engineering product release. (OpenAI’s engineering overview)
CAD, drawings, and simulation
OpenAI says its hardware and infrastructure teams use Codex and ChatGPT to create and revise computer-aided design models, prepare manufacturing drawings, set up simulations, and review designs. The article describes work across mechanical design, electrical engineering, and simulation rather than a single new feature or product tier. (OpenAI’s engineering overview)
The company also describes collaborations that put these workflows into specific engineering settings:
- Chip Ganassi Racing: OpenAI is testing a process that turns 3D scans of existing parts into editable CAD models and manufacturing drawings. CGR engineers review the results for accuracy and manufacturability. (OpenAI’s engineering overview)
- Mazda: OpenAI describes a research collaboration between its research and Forward Deployed Engineering teams and Mazda’s engineers on vehicle design and simulation. The article says GPT-6 Astra in Codex is being used to explore new nose shapes and simulate airflow to reduce drag. (OpenAI’s engineering overview)
- OpenAI’s hardware teams: The company says staff are using the tools in CAD, electronic design, simulation, and design review. These are team workflows described by OpenAI, not a claim that the models can independently approve engineering designs. (OpenAI’s engineering overview)
Human review remains part of the process
OpenAI says partner engineers review model outputs for accuracy and practical use; CGR engineers specifically review CAD models and drawings for accuracy and manufacturability. In a separate device-design side project, two OpenAI team members used GPT-6 Astra to design a prototype device for talking to Codex in under a week. Getting it ready for manufacturing still required several rounds of review and iteration because the model did not consistently account for production limits, tolerances, and assembly details. (OpenAI’s engineering overview)
The update is useful as a view into how Codex is being applied beyond software engineering, especially around CAD iteration and simulation. The post invites engineers, engineering firms, and software vendors to help shape the effort; its linked computer-use research-collaboration form is a general invitation for a small number of software companies with concrete professional workflows to evaluate. That is a partnership invitation, not a public access path to a new engineering product. (OpenAI’s engineering overview; OpenAI's collaboration form)
Sources
- OpenAI, “Accelerating engineering for the physical world,” November 3, 2026: https://openai.com/index/accelerating-engineering-for-the-physical-world/
- OpenAI, “Computer-use research collaboration” form: https://openai.com/form/computer-use-research-collaboration/
Read next
Related coverage- Codex
Codex Composer Predictions Beta Suggests the Next Message in Desktop Threads
OpenAI added composer predictions to Codex in beta. Eligible personal ChatGPT Pro users aged 18 and older can see complete next-message suggestions in the Codex desktop app for supported local and SSH threads, accept them with Tab, edit before sending, and turn the feature off in Settings.
- OpenAI
OpenAI Launches GPT-6 Astra for Computer Use and Complex Work
OpenAI launched GPT-6 Astra on September 3, 2026, for computer use and complex work. Its October 16 update to GPT-6 Pro in ChatGPT adds faster responses, improved plugin and tool use, and parallel agents, rolling out to eligible Pro users.
- OpenAI
OpenAI GPT-6.1 Terra: Availability, Computer Use, and API Pricing
OpenAI began rolling out GPT-6.1 Terra on October 26 in ChatGPT Work and Codex, with the API model identifier `gpt-6.1-terra`. ChatGPT rollout includes Plus, Pro, Business, Enterprise, and Edu, with access depending on plan, region, workspace settings, and rollout timing. For requests up to 272K input tokens, standard API rates are $1 per million input tokens, $0.05 per million cached input tokens, and $5 per million output tokens; long-context, Fast-mode, and cache-write rates differ.
- OpenAI
OpenAI Adds Prompt Presets and Inline Controls to Codex CLI
OpenAI's Codex CLI 0.164.0 release adds reusable prompts in ten numbered `/presets` slots, inline settings for model, reasoning effort, speed, and permissions, plus sign-in options for enterprise MCP connections.
Frequently Asked Questions
What engineering work did OpenAI describe?
OpenAI says its hardware and infrastructure teams use ChatGPT and Codex to create and revise CAD models, prepare manufacturing drawings, set up simulations, and review designs.
What is OpenAI testing with Chip Ganassi Racing and Mazda?
With Chip Ganassi Racing, OpenAI is testing workflows that turn 3D scans of existing parts into editable CAD models and manufacturing drawings. Mazda is a research collaboration exploring vehicle designs through simulation, including aerodynamic work with GPT-6 Astra in Codex.
Did OpenAI announce a generally available engineering product?
The November 3 article describes internal workflows and industry collaborations, calls the work early, and says OpenAI is seeking additional collaborators. It does not announce general availability of a new engineering product.
Get an email when Codex changes its plans, prices or limits
We check every change against Codex's own pages before we send. You also get the weekly AI Catchup; one click unsubscribes.