legal_document_review · energy · workflow
Xcel Energy builds RAG-based chatbot with Databricks Mosaic AI, cutting rate case review from 6 months to 2 weeks
Xcel Energy's rate case review process took up to several months due to complex documentation, while leadership needed insights from hundreds of pages of earnings reports and the legal team needed faster access to customer contract details.
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 · User query submission
Users submit queries covering rate case reviews, legal contracts reviews, and analysis of earnings call reports.
Tools used
Databricks Mosaic AIUnity CatalogFoundation Model APIsVector SearchMLflowModel ServingDatabricks NotebooksApache SparkLangChainMixtral 8x7b-instructLlama 2DBRXClaude Sonnet 3.5AWS Bedrock · partnerAgent Bricks AI GatewayDatabricks SQL
Outcome
Rate cases now take 2 weeks instead of up to 6 months. The project significantly reduced the time taken for rate case reviews and improved data access and insights.
Results
Time saved2 weeks instead of up to 6 months
Volumesignificantly reduced
Grounding & classification
Source type: technical build writeup
41 fields verified against source quotes.
chatbotdocument aienterprise searchragcontractknowledge basepolicy documentmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedenergycycle time reductionemployee productivitytime savedtechnical build writeupfinance opslegal document reviewregulatory reportingrag answering