OpenAI just launched 'Codex', a new AI agent for software engineering
The new Codex agent from OpenAI will be integrated within ChatGPT and aimed at developers
OpenAI has unveiled the launch of a new AI agent designed specifically for software engineering tasks.
Codex, which is now available in preview, allows users to “delegate tasks to a software engineering agent in the cloud”, the company said. The agentic AI tool is powered by codex-1, a version of OpenAI’s o3 reasoning model which is optimized for coding tasks.
During training of codex-1, OpenAI said it aimed to “align outputs closely with human coding preferences and standards”. All told, codex-1 consistently produces "cleaner" code outputs compared to its o3 reasoning model.
“Codex can perform tasks for you such as writing features, answering questions about your codebase, fixing bugs, and proposing pull requests for review; each task runs in its own cloud sandbox environment, preloaded with your repository,” the company said in a blog post.
How OpenAI’s new Codex tool works
The new AI agent is conveniently integrated within ChatGPT, the company explained in a blog post. Users can access Codex through the sidebar in the chatbot and assign it tasks by typing a simple prompt and clicking ‘Code’.
“If you want to ask Codex a question about your codebase, click “Ask”. Each task is processed independently in a separate, isolated environment preloaded with your codebase.”
Codex is capable of reading and editing files, and can run commands such as test harnesses, linters, and type checkers, OpenAI noted. The firm added that task completion typically takes “between 1 and 30 minutes” depending on the complexity of said task.
The tool’s activities can also be monitored in real-time, allowing developers to keep tabs on progress.
Notably, once completed Codex will provide users with "verifiable evidence” of its actions via citations of terminal logs and test outputs.
This, the company explained, allows you to “trace each step taken during task completion”.
“You can then review the results, request further revisions, open a GitHub pull request, or directly integrate the changes into your local environment. In the product, you can configure the Codex environment to match your real development environment as closely as possible.
How to get your hands on the new Codex agent
While Codex is being released in preview initially, it will be rolled out to ChatGPT Pro, Enterprise, and Team users immediately.
In its blog post unveiling the tool, OpenAI said support for Plus and Edu editions will be “coming soon”.
The launch of the new AI agent comes in the wake of OpenAI’s rumored acquisition of Windsurf, a US-based startup specializing in AI coding tools, and highlights the company’s continued push into the AI programming domain.
A host of big tech companies have ramped up expansion of AI tools for software development in the last 18 months, which has become a leading use-case for the technology since the emergence of generative AI in late 2022.
AWS, Microsoft, GitHub, and Google have all expanded AI coding capabilities across their respective product bases.
OpenAI has been equally active on this front, with recent model releases specifically targeting coding capabilities.
The company has been keen to push its GPT-4.1 model as a developers go-to option, but recent benchmark testing raised questions over its effectiveness compared to other leading industry options.
MORE FROM ITPRO
-
Cyber experts issue warning over new phishing kit that proxies real login pagesNews The Starkiller package comes monthly framework updates and documentation, meaning no technical ability is needed
-
Microsoft hails advances in glass data storageNews Project Silica uses lasers to encode data into borosilicate glass, where it stays stable for thousands of years
-
OpenAI's 'Skills in Codex' service aims to supercharge agent efficiency for developersNews The Skills in Codex service will provide users with a package of handy instructions and scripts to tweak and fine-tune agents for specific tasks.
-
Anthropic says MCP will stay 'open, neutral, and community-driven' after donating project to Linux FoundationNews The AAIF aims to standardize agentic AI development and create an open ecosystem for developers
-
Atlassian just launched a new ChatGPT connector feature for Jira and Confluence — here's what users can expectNews The company says the new features will make it easier to summarize updates, surface insights, and act on information in Jira and Confluence
-
GitHub is scrapping some Claude, OpenAI, and Gemini models in Copilot – here's what you need to know and what alternatives are availableNews GitHub Copilot users are urged to switch to the newer models following the retirement cut-off
-
OpenAI's plan to acquire AI coding startup Windsurf ended in disaster – here’s how the deal fell apartNews The acquisition by Cognition comes after a rumored $3bn offer from OpenAI fell through
-
OpenAI is closing in on its biggest acquisition to date – and it could be a game changer for software developers and ‘vibe coding’ fanaticsNews OpenAI is reportedly closing in on a $3 billion deal to acquire AI startup Windsurf.
-
OpenAI wants developers using its new GPT-4.1 models – but how do they compare to Claude and Gemini on coding tasks?News OpenAI says its GPT-4.1 model family offers sizable improvements for coding, but tests show competitors still outperform it in key areas.
-
"OpenAI continues to be our partner on frontier models": Microsoft is open to using a range of AI models in 365 Copilot, but OpenAI remains its go-to choiceNews Citing concerns over performance and cost, Microsoft will look to use a range of models to provide the best experience for Copilot 365 users
