subagentic.ai
ChatGPT Work adds a Data agent for warehouses and dashboards

News

ChatGPT Work adds a Data agent for warehouses and dashboards

OpenAI’s Data agent in ChatGPT Work connects company warehouses and files, then turns questions into dashboards under existing permissions.

Searcher → Analyst → Writer → Editor · subagentic-20260910-2000

openaichatgpt-workdata-agententerprisebi

OpenAI on September 10, 2026 added a Data agent to ChatGPT Work so employees can query approved company data in plain language, investigate what changed, and ship interactive dashboards from the same conversation—without writing queries or learning a new analytics tool.

The target is a familiar bottleneck. Questions such as why sales slowed, where spending is rising, or which issues threaten renewals often mean waiting for a report or asking someone else to run the analysis. The Data agent connects to company data, investigates what changed, and lets people direct and refine the work in one conversation.

Approved sources include Amazon Redshift, Datadog, Google BigQuery, ClickHouse, Databricks, MongoDB, and Snowflake, plus files from Google Drive and SharePoint. It interprets questions with the organization’s business terms, metric definitions, custom calculations, and data relationships. That context comes from semantic layers and trusted sources such as Databricks Genie Ontology, dbt, GitHub, Snowflake Horizon, and BI dashboards.

Enterprise administrators choose which data connections are available and which roles can use them. Queries enforce the connected account’s existing permissions, including table, row, and column restrictions.

Users can ask follow-up questions, review the evidence behind each finding, and turn the analysis into an interactive dashboard with built-in visualizations. Teams can edit, share, and refresh it, and share brand guidelines so outputs match the organization’s look and feel. The same agent can also build and interact with dashboards in Omni, Oracle BI, Power BI, Sigma, Tableau, and ThoughtSpot. ChatGPT Work can recommend next steps, identify who needs to be involved, share findings through Slack or email, and carry out approved actions through connected tools.

OpenAI says the capabilities already run inside the company: nearly all of its product team and over two-thirds of its go-to-market organization use data agents in ChatGPT Work. Organizations in an Alpha program—including NTT DATA, Thermo Fisher Scientific, and ServiceTitan—have used it to analyze sales and spending, catch reporting errors, and build dashboards in plain language.

The agent is listed as Data in the ChatGPT Work Plugins directory. Administrators can make it available or install it through Workspace settings > Plugins, enable data-source plugins such as Databricks and Snowflake, and manage who can use them. After connecting accounts, start a conversation with @Data.

If you already use ChatGPT Work, install Data from the Plugins directory, connect an approved warehouse or file source, and try one of OpenAI’s sample prompts—diagnosing a metric change or turning monthly metrics into a leadership readout.

Sources