customer_support · saas · workflow

RAG with Knowledge Graphs reduces median customer service issue resolution time by 28.6% at LinkedIn

Conventional RAG for customer service treated historical issue tracking tickets as plain text, discarding intra-issue structure and inter-issue relations. Text segmentation further disconnected related content such as a ticket's problem description and its solution, degrading both retrieval accuracy and answer quality.

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 · KG construction from historical tickets
The system constructs a comprehensive knowledge graph from historical customer service issue tickets, retaining intra-issue structure and inter-issue relations.
Tools used
LLMGPT-4BERTE5QdrantNeo4j
Outcome

The KG-augmented RAG system outperformed the baseline by 77.6% in MRR and by 0.32 in BLEU. Deployed at LinkedIn's customer service team, the system reduced median per-issue resolution time by 28.6%, with mean resolution time dropping from 40 hours to 15 hours.

What failed first

The baseline embedding-based retrieval approach lost structural ticket relationships by compressing documents into plain-text chunks, and text segmentation split tickets such that problem descriptions and their solutions appeared in separate chunks, causing incomplete answers.

Results
Time saved28.6%
Volume77.6%
Running sinceapproximately six months
Source

https://arxiv.org/html/2404.17723

How we source this →

Grounding & classification
Source type: technical build writeup
37 fields verified against source quotes.
document aienterprise searchknowledge searchragknowledge basesupport ticketfailure mode describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwareaccuracy improvementemployee productivityresolution time reductiontechnical build writeupcustomer supportit supportticket triageextract classify routerag answering