Dataiku has launched Dataiku Headless, a new capability that brings its natural-language agentic interface, Cobuild, into the coding tools developers already use every day.

Unveiled at Succeed, the company's annual flagship conference, Headless lets developers build, modify and investigate Dataiku projects from inside their coding environment. Developers can ask a coding agent to create or change data pipelines, models, dashboards and agents as Dataiku projects, with the work remaining visible, reviewable and governed for the wider team.

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. It acts as the control surface a coding agent uses to inspect and operate Dataiku, calling on Cobuild whenever a task requires creating or changing a project.

The launch also targets migration work. A coding agent can analyse an Excel workbook or an Alteryx workflow and instruct Cobuild to rebuild it as a Dataiku project, helping teams modernise legacy data work without starting from scratch.

Dataiku says the move answers a growing enterprise problem: AI coding agents are speeding up data and software development, but the resulting work can be hard for other teams to inspect, govern, maintain and put into production. Headless aims to keep that speed while keeping governance intact.