compliance_monitoring · education · workflow
North Dakota University System builds a generative AI Policy Assistant on Databricks to automate compliance search
NDUS data teams spent hours manually searching through thousands of policy documents, state laws, contracts, and codes to ensure compliance, with no shared infrastructure to collaborate or scale use cases across the system's 11 institutions.
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 · Plain English query via API
Users prompt the LLM within the system with plain English via an API.
Tools used
Databricks Data Intelligence PlatformLlama 2DBRXFoundation Model APIsUnity CatalogVector SearchMLflowSpark Declarative Pipelines
Outcome
NDUS reduced time to bring new insights to market from one year to six months, launched Policy Assistant which synthesizes over 3,000 public PDFs for instant plain-English policy queries, and increased team productivity.
Results
Time savedfrom one year to six months
Volume3,000
Grounding & classification
Source type: vendor customer story
31 fields verified against source quotes.
enterprise searchknowledge searchragsummarizationknowledge basepolicy documentmetric backednamed customerproduction runtime claimedtools describedworkflow describededucationcycle time reductionemployee productivitytime savedvendor customer storyback office opscompliance monitoringrag answering