customer_support · services · workflow

Thomson Reuters Labs builds RAG-powered customer support assistant using GPT-4 and milvus to reduce resolution times

Customer support agents at Thomson Reuters faced cognitive overload navigating hundreds of thousands of knowledge base articles and CRM tools, while resolution knowledge was siloed in individual agents with no structured way to share it across the team.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Ingest and chunk source data
Knowledge base articles and CRM data are processed into text chunks.
Tools used
GPT-4milvusall-MiniLM-L6-v2huggingface
Outcome

Thomson Reuters Labs deployed a RAG-based chatty interface that provides customer support agents with accurate, product-specific resolutions grounded in curated domain knowledge, reducing resolution times compared to an ungrounded GPT-4 response.

Results
Time savedreduce resolution times
Source

https://medium.com/tr-labs-ml-engineering-blog/better-customer-support-using-retrieval-augmented-generation-rag-at-thomson-reuters-4d140a6044c3

How we source this →

Grounding & classification
Source type: technical build writeup
22 fields verified against source quotes.
chatbotknowledge searchragsupport agentknowledge basesupport ticketfailure mode describednamed customerproduction runtime claimedtools describedworkflow describedlegalprofessional servicesaccuracy improvementresolution time reductiontechnical build writeupcustomer supportrag answering