AI Developer

OpenAI Codex in Jira

Hand a Jira issue to OpenAI Codex and get a working implementation on a branch, typically within minutes. A summary lands as a comment on the ticket, and your team reviews and merges as usual.

It runs on your repositories with your own credentials, and it works without Rovo.

AI Developer panel on a Jira issue with Implement, Enhance Description, and Inquiry actions

See it in action

Loads the video from YouTube when you click play. Watch on YouTube

What AI Developer for OpenAI Codex does

Implement tickets from Jira

Click Implement on an issue. The AI plans the work, implements it step by step, commits and pushes to a dedicated branch. Connect GitHub, GitLab, Bitbucket or any self-hosted Git.

Ask, clarify and refine

Use Inquiry to ask questions about a ticket or check requirements against your real code. Not happy with a result? Mention the app in a comment and it updates the same branch. Learn more

Your AI, your infrastructure

Use an OpenAI API key or your Codex subscription. Choose the Codex model that fits your budget.

Multiple repositories

Configure more than one repository per Jira project and route issues to the right codebase.

Isolated runners and regions

Each job runs in its own isolated runner, with EU, German and US regions available. Enterprise controls

Better results with repo guidance

Add a AGENTS.md to the root of your repository with build commands and conventions. The AI picks it up automatically.

How it works

Start from the issue

Click Implement in the AI Developer panel on any Jira issue — no extra setup per ticket.

AI analyzes the task

It reads the issue summary and description to understand what's being asked.

AI generates a solution

Claude Code or OpenAI Codex writes the implementation — code, tests, and dev notes as applicable.

Code pushed to branch

The implementation is committed and pushed to a dedicated branch in your configured repository.

Comment posted on issue

A comment on the Jira issue links the branch and summarizes what changed, so the team can review.

Comment feedback to refineOptional

Not quite right? Mention AI Developer in a comment with what to change, and it updates the same branch.

Need a review step before code is written?

Add Spec Driven Development

For larger or less clear tickets, Spec Driven Development creates a spec your team reviews and edits in Jira before any code is written. It works with OpenAI Codex or Claude Code.

Frequently asked questions

Do I need an Atlassian Rovo license?

No. The app works on its own and does not depend on Rovo.

Who pays for the AI usage?

You do, directly with your AI provider. You connect your own credentials, so OpenAI Codex usage is billed to your account. Pricing and licensing for the app itself are shown on its Atlassian Marketplace page.

Will the AI change my main branch?

No. Work is pushed to a new ai/* branch. A developer reviews and merges it.

How do I set it up?

Add your repository and AI credentials in the Jira project settings. The documentation walks through it step by step.

Is there a version for Claude Code?

Yes: AI Developer for Claude Code.

Get AI Developer for OpenAI Codex

Available on the Atlassian Marketplace.

Get it for OpenAI Codex Read the docs