ChatGPT Work adds Data agent for enterprise data analysis

OpenAI has introduced a new Data in ChatGPT Work agent for analyzing company data through natural language. It can investigate questions, generate answers, build dashboards, and support follow up actions in the same conversation. Data connects to sources including Amazon Redshift, Google BigQuery, Databricks, MongoDB, and Snowflake, and can also use files from Google Drive and SharePoint.

The agent can interpret company specific terminology, metric definitions, calculations, and data relationships using sources such as dbt, GitHub, Snowflake Horizon, Databricks Genie Ontology, and existing BI dashboards. Administrators control available connections and role access, while queries preserve existing table, row, and column permissions.

Users can inspect the evidence behind findings, ask follow up questions, and turn results into editable and shareable dashboards. Data can also work with Omni, Oracle BI, Power BI, Sigma, Tableau, and ThoughtSpot through plain language, share findings through Slack or email, and carry out approved actions through connected tools. Workspace administrators can enable Data from the Plugins settings and configure the required data source connections before users start a conversation with @Data.