Cognite VISION: No-code data engineering for domain experts

Problem Statement

Cognite Data Fusion (CDF) offers a powerful suite of tools for industrial data operations, but its adoption remains limited to highly technical users such as data engineers, data scientists, and developers. Today, creating data transformations, writing functions, deploying models, and generating insights in CDF typically requires:

• Knowledge of Spark SQL for transformations
• Python programming for custom functions
• Understanding of data modeling concepts
• Manual deployment and orchestration

This steep technical barrier restricts broader usage, particularly among domain experts like production operations engineers, maintenance supervisors, or process owners who possess deep contextual knowledge but lack coding skills. As a result, CDF usage and ROI are throttled by dependence on a small pool of technical resources.

Vision

Empower every domain expert to become a CDF power user — without writing a single line of code.

Proposed Solution: Cognite vision – AI-Powered No-Code Experience

Introduce Cognite VISION, an out-of-the-box AI agent integrated into CDF that uses LLMs to eliminate the need for coding expertise.

With VISION, a user can simply ask:

"Join sensor data from the compressor with maintenance logs and create a dashboard to predict downtime every 6 hours."

VISION handles the rest:

• Interprets the intent using an LLM
• Writes Spark SQL transformations behind the scenes
• Creates and deploys Python functions for processing or inference
• Builds contextualized data models
• Schedules pipelines
• Deploys insights to dashboards or external apps

All within seconds, fully auditable, and explainable for enterprise transparency.

Key Features

•  Natural Language Interface: Ask for transformations, models, or dashboards in plain language
• Automatic Backend Generation: LLMs write code, configure parameters, and deploy pipelines
• One-Click Deployment: From request to production in a few clicks or a single prompt
• Insight Builder: Automatically recommends and generates insights based on domain context
• Governed Execution: Every AI-generated artifact passes through existing governance and logging frameworks