A 'stream' (formerly known as a 'trigger') in the platform is essentially a tool for automatically creating a queue of verbatims, which satisfy specific label or metadata conditions.
Streams are frequently used in the platform to facilitate automated processing of requests, with the platform acting as the interpreter of an unstructured communication. The platform understands and adds structure to the communication and makes it available downstream for processing.
This queue is made available to downstream applications via the Communications Mining API endpoints. The outputs from the API are machine readable objects in JSON format, containing all of the associated metadata, verbatim text, and the associated labels as structured data points.
For an explanation on how to set up or update a stream, please see here.