back_office_ops · energy · workflow
Schneider Electric leverages Retrieval Augmented LLMs on SageMaker to ensure real-time updates in their CRM systems
Schneider Electric's account teams had to manually sort through new customers daily and link them to the correct parent entity in their CRM. Using LLMs alone was insufficient because their knowledge is limited by their training cutoff date, causing them to miss recent acquisitions, market news, and corporate restructurings.
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 · New account triggers linking need
New customers are added daily and require sorting and linking to the proper parent entity.
Tools used
Amazon SageMaker JumpStartFlan-T5-XXLLangChainSerperAmazon SageMaker Studio
Outcome
Domain-specific prompt engineering boosted overall linking accuracy from 55% to 71%, reduced manual effort in linking workflows, and delivered faster data access to downstream analytics teams.
What failed first
The initial blanket prompt approach achieved only 55% accuracy and did not generalize well to education or healthcare domains, where the notion of 'parent company' is not meaningful.
Results
Volume71%
Running sinceearly 2023
Grounding & classification
Source type: technical build writeup
25 fields verified against source quotes.
data extractionragknowledge basefailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedenergymanufacturingaccuracy improvementemployee productivitytechnical build writeupback office opssales opsdata sync enrichmentrag answering