Introducing OpenAI Codex: Your New AI Software Engineering Agent

OpenAI has unveiled Codex, a powerful new AI software engineering agent designed to transform the way developers work. More than just a code completion tool, Codex acts as a collaborative partner, capable of handling a wide range of tasks across the entire software development lifecycle. Codex is not just an inline tool that can help software developers complete their code, or suggest better code. This is a complete overhaul, this time OpenAI introduced a complete sandbox with your entire repository and an AI companion that can see the entire lot. Let’s take a deeper look at this amazing new release from the creators of ChatGPT.

What Is Codex (in a nutshell)?

Codex is a cloud-based software engineering agent accessible today to ChatGPT Pro, Team, and Enterprise users (with Plus and Edu support coming soon). At its core, Codex is a cloud-based AI agent powered by codex-1, a version of OpenAI’s o3 model specifically optimized for software engineering, fine-tuned via reinforcement learning on real-world coding tasks to produce human-like, style-consistent patches that pass tests in a single iteration. Its primary focus is to assist developers by performing tasks such as writing features, answering questions about a codebase, fixing bugs, and proposing pull requests. Codex operates in isolated cloud environments preloaded with your codebase, allowing it to work on multiple tasks in parallel.

Codex Interface – Image credit: openai.com

How Codex Works

Task Submission: Within ChatGPT’s sidebar, you assign a task, like “Code”, “Ask”, or “Fix” and Codex spins up an isolated sandbox environment containing your repo.
Execution & Monitoring: Codex reads and edits files, runs linters, test harnesses, and type checkers, and you can watch progress in real time as tasks complete in 1–30 minutes.
Verification & Integration: Upon completion, Codex commits changes in its environment and attaches verifiable citations, terminal logs and test outputs, so you can trace every step before merging or requesting revision.
Customization: AGENTS.md files within your repo guide Codex on project-specific practices and commands, optimizing performance much like onboarding instructions for a human teammate.

Key Features

Parallel Tasking: Deploy multiple agents concurrently on independent tasks, akin to managing an engineering squad: ideal for on-call rotations or morning to-do lists.
Deep Code Understanding: Codex-1’s training on extensive codebases enables it to align with human preferences, producing cleaner patches than general-purpose models.
Transparent Outputs: Citations of logs and test results provide auditability and foster trust, crucial for safety as AI assumes greater coding responsibilities.
Integrated CLI: The Codex CLI brings a lightweight agent to your terminal, powered by a lower-latency codex-mini-latest model for rapid code Q&A and editing, with seamless ChatGPT account sign-in and free API credits for Pro/Plus users.

How is Codex Different from GitHub Copilot?

While GitHub Copilot, also powered by a form of Codex, is primarily an AI pair programmer providing real-time code suggestions within an Integrated Development Environment (IDE), OpenAI Codex offers a more expansive and autonomous approach.

Think of Copilot as a highly intelligent autocomplete and suggestion tool that works inline as you write code in your IDE. It’s excellent for speeding up the actual writing of code snippets and boilerplate.

Codex, on the other hand, functions as a delegated agent that can take on larger, more complex tasks independently. You can assign Codex a higher-level goal, like “implement a login feature” or “fix all the reported bugs in this module,” and it will work in its own environment to achieve that goal, including reading and editing multiple files, running tests, and debugging. This allows developers to offload significant tasks and focus on more complex problem-solving and design. While Copilot is integrated directly into your IDE for immediate assistance, Codex can be accessed through interfaces like ChatGPT and the Codex CLI, offering more flexibility for different workflows and custom integrations.

Detailed Functions Of Codex

Codex is designed to accelerate more than just the initial code writing phase. By handling tasks autonomously in parallel environments, it can significantly speed up various aspects of the software development workflow:

Feature Development: Delegate the implementation of well-defined features to Codex, freeing up developers to work on other parts of the project.
Bug Fixing: Assign bug reports to Codex, which can analyze the codebase, identify the issue, propose and test a fix.
Code Understanding: Ask Codex questions about unfamiliar parts of a codebase to quickly get context and explanations.
Refactoring and boilerplate: Automate repetitive coding tasks like refactoring code or writing boilerplate, allowing developers to focus on more creative work.
Testing: Codex can write and run tests, ensuring code quality and reducing the manual effort required for testing.
Code Reviews and Pull Requests: Codex can propose pull requests with its completed changes and provide verifiable evidence of its actions through logs and test outputs, making the review process more efficient.
Task Delegation: Assign complex coding tasks using natural language prompts, and Codex will work independently to complete them.
Isolated Environments: Each task runs in a secure, sandboxed cloud environment preloaded with your codebase and dependencies. This ensures safety and prevents unintended side effects on your local machine.
Parallel Execution: Codex can handle multiple tasks concurrently, allowing developers to multitask more effectively.
Code Reading and Editing: Codex can read and modify files within its environment to implement changes.
Command Execution: It can run terminal commands, including test harnesses, linters, and type checkers, to verify its work and ensure code quality.
Verifiable Actions: Codex provides logs and test outputs, allowing developers to trace each step it took to complete a task and verify the correctness of its work.
Guidance via AGENTS.md: Developers can include AGENTS.md files in their repositories to provide Codex with guidance on codebase navigation, testing procedures, and project standards.
Iterative Problem Solving: Codex can iteratively run tests and refine its approach until it achieves a passing result, similar to how a human developer debugs.
Integration Capabilities: Codex can be accessed through interfaces like ChatGPT and a command-line interface (CLI), offering flexibility in how developers interact with it.

This ability to delegate and parallelize tasks across the development lifecycle allows developers to manage their workload more effectively and deliver projects faster.

What we would like to be able to do

With the amount of AI Coding assistants we currently have, it is very possible for a software developer to ask the agent to rewrite a specific piece of code or optimise a code flow. This is easily done as the piece of code does not life within the entire context of the whole project. This makes it viable for AI Coding assistants as the amount of overhead processing power needed to process a specific piece of code with knowledge of the entire project, will make the suggestion multitudes more complex and time consuming. However, this time round, codex does have sight of your entire project. Although we can assign bugs to it and it will assess and suggest fixes, we would also like to be able to send the entire codebase to Codex for optimisation. According to OpenAI refactoring is already possible, so will it be possible to assign a feature like ‘”Make the login screen look more appealing for users”? If so, what would this implication be for Search engine optimisation seeing as you would probably also be able to ask for SEO tips and implementations for websites.

Something we are really looking forward to, if it is possible, would be to create a site or app for one device (example computer screen) and then assign the mobile friendly version to Codex for implementation. That tests though, running tests is one thing, but can it fix the code if the tests fail? Let’s be honest, running unit tests is not the most difficult task, so to be able to run tests is not an achievement. But being able to either fix code after tests, or just create unit tests for us would be amazing (show me one Software Developer that likes to create unit tests…)

Unfortunately, Codex is only available to Pro users and those with organisation accounts. It does, however, state that this access is “Access to a research preview of Codex agent” (as per the feature comparison of subscriptions – https://openai.com/chatgpt/pricing/). As such, we cannot give a review of it yet as we do not have either of those subscriptions (Pro being US$200 per month– which is insane). Once it comes to the plus subscription, we will take it for a full test drive and revert back with our impressions and usability scenarios.

Artificial Intelligence