Dataiku has announced Dataiku Headless, a new capability that brings Dataiku Cobuild, its natural-language agentic interface, into the coding tools that technical teams already use every day.
Coding agents like Claude Code and Codex have changed how technical teams work, making it faster than ever to go from an idea to a working script. The bottleneck isn’t how fast that work gets built anymore — it’s how few people can actually see it once it’s done. The fix isn’t asking fewer people to build; it’s giving more people a way to see what got built. Headless is designed to do exactly that. It gives developers a way to keep working in the coding agent they already trust, to create and modify data pipelines, models, dashboards, and agents as Dataiku projects.
Headless brings the same governed, natural-language experience that technical teams already know from Dataiku Cobuild to the environment they don’t want to leave. Under the hood, Headless is the control surface a coding agent uses to inspect and operate Dataiku, calling on Cobuild whenever a task requires creating or changing a project. With Headless, developers can:
- Build from a coding agent: Developers can ask their coding agent to find the relevant Dataiku context and delegate the building work to Cobuild, which creates it in Dataiku as a visual flow, datasets, transformations, models, custom Agents, and other assets that the team can inspect.
- Migrate legacy workflows: Work built outside Dataiku, like an Excel workbook or an Alteryx workflow, can be analyzed by a coding agent, which then instructs Cobuild to rebuild it as a governed, visual Dataiku project, turning a one-time code translation into a maintained pipeline. Coding agents can repeat this hundreds or thousands of times, making large-scale modernization projects drastically quicker and saving developers hours in manual migration work.
- Investigate and support Dataiku environments: Administrators can ask their coding agent to find jobs that have been failing across multiple projects. Headless can help diagnose issues and remediate them by changing project or administrative settings.
“Developers aren’t going to stop working in Claude Code or Codex, and we don’t think they should have to,” said Jed Dougherty, SVP of AI & Platform at Dataiku. “What they need is a way to turn that speed into something the rest of the business can actually see, review, and run in production. That’s what Dataiku Headless does — it meets technical teams in the tools they already trust, and hands back a Dataiku project instead of a script only they can read.”
Availability
Dataiku Headless is available as a plugin on the Claude Code and Codex marketplaces and is compatible with Cursor, Snowflake CoCo, GitHub Copilot, AWS Kiro, and other agentic coding tools.
