customer_support · saas · workflow
Elastic builds a GenAI proof of concept for automated customer support case summaries and draft replies
Elastic's support engineers spent significant time creating case summaries for escalations and transitions between engineers, while meeting SLA-driven timely response requirements was resource-intensive.
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 · CRM button triggers workflow
A custom button added to all cases in Salesforce calls an external endpoint to initiate the case summary workflow.
Tools used
Vertex AIGoogle Cloud PlatformSalesforce Service Cloud · partnerGoogle Cloud FunctionPub/SubSalesforce ChatterElasticsearch
Outcome
Elastic moved from proof of concept to an approved project to build a scalable Support AI Chat Assistant, with a plan to integrate Elasticsearch via a retrieval augmented generation architecture for improved response accuracy.
What failed first
The initial Vertex AI proof of concept produced only a 15.67% positive response rate — much lower than expected — because the LLM was trained on public data and lacked access to Elastic's product documentation and internal knowledge base articles, leaving it unable to address technical support queries accurately.
Results
Time saved44
Volume940
Grounding & classification
Source type: technical build writeup
31 fields verified against source quotes.
content generationsummarizationknowledge basesupport ticketfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementemployee productivitytechnical build writeupcustomer supportticket triageai draft human approvalcase to summary