Dataiku Introduces Headless to Bring Governed Data and AI Workflows to Agentic Coding Tools
Dataiku has announced Dataiku Headless, a new capability that brings its natural-language agentic interface, Dataiku Cobuild, into the coding tools used by technical teams.
Coding agents such as Claude Code and Codex are changing how developers work, accelerating the journey from an idea to a functional script. However, as development becomes faster, ensuring that the resulting work can be accessed, reviewed and managed by the wider organisation remains a challenge. Dataiku Headless aims to address this by allowing developers to continue working with their preferred coding agents while creating and modifying data pipelines, models, dashboards and AI agents as Dataiku projects.
The new capability extends the governed, natural-language experience offered by Dataiku Cobuild into existing coding environments. It provides coding agents with a control interface to inspect and operate Dataiku, calling on Cobuild when tasks involve creating or modifying projects.
With Dataiku Headless, developers can:
- Build directly from coding agents: Developers can ask their preferred coding agent to identify relevant Dataiku context and delegate development tasks to Cobuild. The platform then creates visual flows, datasets, transformations, models, custom agents and other assets within Dataiku, allowing teams to inspect and manage the resulting projects.
- Migrate legacy workflows: Existing work created outside Dataiku, including Excel workbooks and Alteryx workflows, can be analysed by coding agents and rebuilt through Cobuild as governed, visual Dataiku projects. This turns one-time code conversions into maintainable pipelines. Coding agents can repeat the process across hundreds or thousands of workflows, accelerating large-scale modernisation initiatives and reducing the time developers spend on manual migration.
- Investigate and manage Dataiku environments: Administrators can use coding agents to identify recurring job failures across multiple projects, investigate their causes and implement corrective measures. Headless can support diagnosis and remediation by modifying project-level 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.”
Dataiku Headless is available as a plugin through the Claude Code and Codex marketplaces. It is also compatible with Cursor, Snowflake CoCo, GitHub Copilot, AWS Kiro and other agentic coding tools.
