Dataiku has launched Headless, a capability that enables developers to build, migrate and manage governed data and AI projects directly from agentic coding tools including Claude Code, Codex and Cursor.
Dataiku has introduced Dataiku Headless, a new capability designed to connect its governed data and Artificial Intelligence platform with the agentic coding tools increasingly used by technical teams.
The technology brings Dataiku Cobuild, the company’s natural-language agentic interface, into development environments including Claude Code, Codex and Cursor, allowing developers to create and modify data pipelines, models, dashboards and AI agents without leaving their preferred coding tools.
The launch addresses a growing challenge for organisations adopting agentic coding tools. While these technologies can accelerate software development, the resulting scripts and applications may be difficult for other teams to inspect, maintain and govern.
Dataiku Headless is designed to address this issue by allowing developers to work within their existing coding environments while creating projects that can be reviewed and managed through the Dataiku platform.
The capability acts as a control interface between coding agents and Dataiku, allowing agents to inspect and operate the platform while using Cobuild to create or modify projects.
Developers can instruct their coding agents to identify relevant Dataiku information and delegate development tasks to Cobuild.
The resulting work is created within Dataiku as visual workflows, datasets, transformations, models and custom AI agents that other team members can inspect.
Supporting workflow migration and modernisation
Headless also supports the migration of legacy workflows into governed Dataiku projects.
For example, developers can use coding agents to analyse existing Excel workbooks or Alteryx workflows before instructing Cobuild to recreate them as visual Dataiku projects.
According to Dataiku, this approach can accelerate large-scale modernisation initiatives by automating repetitive migration tasks that would otherwise require extensive manual development.
The company says coding agents can repeat these processes across hundreds or thousands of workflows, helping organisations convert existing assets into maintained data pipelines.
Headless also provides capabilities for investigating and supporting Dataiku environments.
Administrators can use coding agents to identify failed jobs across multiple projects, diagnose potential issues and make changes to project configurations or administrative settings.
These capabilities are intended to help technical teams manage increasingly complex data and AI environments while maintaining governance and operational visibility.
Jed Dougherty, SVP of AI & Platform at Dataiku, said: “Developers aren’t going to stop working in Claude Code or Codex, and we don’t think they should have to. 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 through the Claude Code and Codex marketplaces.
The capability is also compatible with Cursor, Snowflake CoCo, GitHub Copilot, AWS Kiro and other agentic coding tools.
The launch extends Dataiku’s approach to governed AI development by connecting agentic coding environments with a platform designed to make data and AI projects accessible, manageable and reusable across organisations.
