Discovery Overview
Discovery identifies unknown or emerging topics in customer conversations. It extracts key conversation subjects and assigns sentiment values (positive, neutral, or negative) to help businesses understand the reasons for customer contacts and how customers feel about specific aspects of the business or product.
How does it work?
Administrators create prompts that instruct the AI on what to look for in interaction transcripts. The AI processes a sample of transcripts and generates a list of topic tags. Administrators refine this list by accepting or blocking specific tags. Once refined, the AI applies the prompt to large sets of historical data or a percentage of new, incoming interactions.
The system applies the resulting tags to interaction records. Users can view and filter these tags in Discovery Analytics dashboards using widgets like tag clouds. Users can also select a tag within an interaction record to navigate directly to the specific point in a transcript where the topic was discussed.
Use Cases and Benefits
- Identify reasons for customer cancellations.
- Track reasons for incoming calls to allocate resources.
- Detect complaints about specific services and products.
- Monitor customer sentiment related to specific topics.
- Review conversation topics without reading full interaction transcripts.
Dependencies
- Interaction transcripts are required.
- For voice services, call recording must be turned on globally or at the service level.
- For voice services, either real-time or historical Speech-to-Text transcription must be configured for the service.
- For chat services, no additional configuration is required.
< Previous