it_support · saas · workflow
ElasticGPT: Elastic's internal RAG-based generative AI assistant for secure employee knowledge discovery
Elastic's workforce lacked a secure, context-aware internal knowledge assistant, while employees using unsanctioned external AI tools ('shadow AI') with sensitive company data posed compliance risks.
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 · Employee submits a query
A user asks a question within the ElasticGPT interface.
Tools used
ElasticsearchElastic CloudEUIElastic ObservabilitySmartSourceGPT-4oGPT-4o-miniLangChainKibanaReactKubernetesOktaAzure · partnerEnterprise ConnectorsElastic APMServiceNow
Outcome
ElasticGPT is already slashing redundant IT queries and creating employee efficiencies, while reducing the potential impact of shadow AI by providing secure access to multiple LLMs.
What failed first
An early attempt using Hugging Face's Chat UI was abandoned when its limitations became clear as users demanded custom features, prompting a switch to Elastic's own EUI.
Results
Volumeslashing redundant IT queries
Grounding & classification
Source type: technical build writeup
39 fields verified against source quotes.
conversational aienterprise searchknowledge searchragknowledge basefailure mode describedmetric backednamed customerproduction runtime claimedsource backedtools describedvendor confirmedworkflow describedsoftwaredeflection rateemployee productivitytechnical build writeupback office opsit supportautonomous resolutionrag answering