Deskhero's AI capability of suggested replies works by leveraging advanced technologies. Here are some key aspects of its functionality:
Use case 1
Embeddings Generation - Each resolved ticket, knowledge base article, and scraped website data is sent to OpenAI Embeddings API to generate embeddings vectors. These vectors capture the semantic meaning of the data.
Use case 2
Vector Database - The generated embeddings vectors are stored in a vector database, allowing for efficient and fast retrieval of relevant data.
Use case 3
ChatGPT Integration - When a query is received, Deskhero's AI runs it against OpenAI Embeddings API to find similar and relevant data. The relevant data is then passed to ChatGPT, which provides human-like responses based on the attached data.
Use case 4
Use Case 4: Search and Suggested Replies - The AI's responses can be presented as search results or suggested replies for support agents. This ensures that agents have access to accurate and helpful information when resolving tickets.
