Extract meaningful insights from unstructured text by using a pre-trained model in Data 360 for zero-shot topic classification. This capability is now generally available and includes some changes since the beta release.
Where: This change applies to Lightning Experience in Enterprise, Performance, Unlimited, and Developer editions.
When: This functionality is available starting in May 2026.
Why: Classify short, intent-rich text, such as sales notes, support cases, and product reviews. Classify text in multiple languages with minimal setup. This task-specific model is a scalable, cost-effective alternative to large language models (LLMs). It offers lower latency and faster time to value.
How: From the AI Models tab in Data 360, select Classify to use the default pre-trained classification model. To use the activated model’s outputs , go to the Integrations tab of the model details, and then configure a predict job, flow, or batch data transform. Apply topic classification in reporting and queries.
