on Friday, launched Codex, a cloud-based software engineering agent that can work on many tasks in parallel.
The agent can perform tasks including writing features, answering questions about your codebase, fixing bugs, and proposing pull requests for review, the company said.
“Codex is powered by codex-1, a version of OpenAI o3 optimised for software engineering. It was trained using reinforcement learning on real-world coding tasks in a variety of environments to generate code that closely mirrors human style and PR preferences, adheres precisely to instructions, and can iteratively run tests until it receives a passing result,” said OpenAI.
While the company started to roll out Codex to ChatGPT Pro, Enterprise, and Team users on Friday, support for Plus and Edu is coming soon.
With Codex, each task is processed independently in a separate, isolated environment preloaded with the user’s codebase. It can read and edit files, and run commands including test harnesses, linters, and type checkers.
Completion of tasks will take anywhere between 1 and 30 minutes, depending on complexity. It also allows users to monitor Codex’s progress in real time.
.thumbnailWrapper{
width:6.62rem !important;
}
.alsoReadTitleImage{
min-width: 81px !important;
min-height: 81px !important;
}
.alsoReadMainTitleText{
font-size: 14px !important;
line-height: 20px !important;
}
.alsoReadHeadText{
font-size: 24px !important;
line-height: 20px !important;
}
}
“Like human developers, Codex agents perform best when provided with configured dev environments, reliable testing setups, and clear documentation,” a press release from the company said.
Giving importance to security and transparency, OpenAI said it designed the agent in a way that allows users to verify its outputs.
“Users can check Codex’s work through citations, terminal logs and test results. When uncertain or faced with test failures, the Codex agent explicitly communicates these issues, enabling users to make informed decisions about how to proceed. It still remains essential for users to manually review and validate all agent-generated code before integration and execution,” it added.
