customer_support · saas · workflow

Elastic builds a RAG-based knowledge library to power the Elastic Support Assistant

Elastic's LLM foundational training was insufficient for technically deep product questions; the knowledge base was split across Swiftype and Appsearch instances creating tech debt; and most ingested documents lacked the summaries needed for effective semantic search.

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 · Support articles ingested into Elasticsearch
Technical support articles authored by Support Engineers are stored in Elasticsearch and serve as a key information source for the Support Assistant.
Tools used
ElasticsearchELSEROpenAI GPT3.5 TurboCrawleeGoogle Cloud RunEUI Markdown EditorBM25
Outcome

Elastic built a knowledge library with vector embeddings for more than 300,000 documents and over 128,000 AI-generated summaries averaging 8 questions each, representing a 10x improvement for semantic search results and enabling the Support Assistant to answer a much broader range of questions.

What failed first

Fine-tuning a custom model was explored and rejected because it required question-answer pairing that did not match the existing data set. Using the first 280 characters of each document as a summary led to poor search relevancy. Passing larger text passages as context to the LLM decreased accuracy.

Results
Volumemore than 300,000
Source

https://www.elastic.co/search-labs/blog/genai-customer-support-building-a-knowledge-library

How we source this →

Grounding & classification
Source type: technical build writeup
35 fields verified against source quotes.
chatbotenterprise searchknowledge searchragsummarizationknowledge basefailure mode describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwareaccuracy improvementtime savedtechnical build writeupcustomer supportit supportdocument to recordrag answering