Introducing Command R+: Our new, most powerful model in the Command R family.
A major provider of CRM and ERP software wanted to provide a better support Q&A experience that could report on transactional data. To achieve this, it worked with Cohere to build a support assistant that could answer common questions with conversational responses based on product documentation and internal knowledge bases.
A major provider of CRM and ERP software wanted to provide a better support Q&A experience that could report on transactional data. To achieve this, it worked with Cohere to build a support assistant that could answer common questions with conversational responses based on product documentation and internal knowledge bases.
The customer used Cohere Command and Rerank with retrieval-augmented generation (RAG) to build a conversational support app. Users could ask detailed technical questions and get relevant responses, along with citations.
The customer used Cohere Command and Rerank with retrieval-augmented generation (RAG) to build a conversational support app. Users could ask detailed technical questions and get relevant responses, along with citations.
STEP 1.
Cohere Command generates queries based on conversation context and support questions
STEP 2.
Connectors query support documentation site using legacy internal search tools
STEP 3.
Cohere Rerank sorts collected responses based on semantic relevance to the original query
STEP 4.
Based on relevant responses, Cohere Command generates a conversational response to questions, along with citations
Better user support experience
Higher employee satisfaction
Fewer support tickets
Cohere’s retrieval prioritizes accurate responses and citations
Rerank comes with connectors to common data sources
Rerank can be fine-tuned to further improve domain performance
Cohere’s powerful inference frameworks optimize throughput and reduce compute requirements
Cohere models can be accessed through a SaaS API, on cloud infrastructure (Amazon SageMaker, Amazon Bedrock, OCI Data Science, Google Vertex AI, Azure AI), and private deployments (virtual private cloud and on-premises)
Over 100 languages are supported, so the same topics, products, and issues are identified the same way