North Dakota University System builds a GenAI 'Policy Assistant' on Databricks for instant policy search
The North Dakota University System (NDUS) used the Databricks Data + AI Platform with Llama 2/DBRX, Foundation Model APIs, Unity Catalog and AI Search to build 'Policy Assistant,' a GenAI application that synthesizes over 3,000 public policy PDFs so staff can query regulations in plain English and get answers with page references and links in seconds instead of hours. The system cut NDUS's time to bring new data insights to market from one year to six months, 10-20x faster than manual policy search.
Overview
The North Dakota University System (NDUS) used the Databricks Data + AI Platform with Llama 2/DBRX, Foundation Model APIs, Unity Catalog and AI Search to build 'Policy Assistant,' a GenAI application that synthesizes over 3,000 public policy PDFs so staff can query regulations in plain English and get answers with page references and links in seconds instead of hours. The system cut NDUS's time to bring new data insights to market from one year to six months, 10-20x faster than manual policy search.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Without a modernized data and AI platform, NDUS data teams spent considerable time wading through pages, references, codes and contracts across thousands of internal policies and state laws to ensure regulatory compliance, relying solely on institutional knowledge and people, which limited their ability to share these resources and slowed users searching for what a policy actually said.
The solution
NDUS expanded its existing Databricks Data + AI Platform on Azure into generative AI, testing open source LLMs before choosing Llama 2 (and later DBRX), using Foundation Model APIs to build applications without custom model deployment complexity, Unity Catalog for unified access controls, and AI Search for automatic data synchronization, to build 'Policy Assistant,' a low-risk automated search and response application built in six months.
Reported business value
NDUS reduced the time to bring new insights to market from one year to six months, achieved 10-20x faster policy search and response versus manual methods, eliminated procurement time and costs by using its existing Azure/Databricks relationship, and Policy Assistant increased team productivity by letting users avoid manually searching five different sites for one document.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other education entries in the register.
Open Universities Australia triples lead qualification with generative AI agents
Open Universities Australia (OUA) used LivePerson's AI Studio to build an LLM-powered generative AI agent that handles initial prospective-student inquiries, replicating the conversational style of human advisors. The agent achieved 3x lead qualification rates compared to self-searching students and 2x compared to OUA's prior scripted chatbot, with an average response time of 6.3 seconds versus roughly 2 minutes for human advisors.
Open Universities Australia· AustraliaLivePerson AI Studio
Miami Dade College boosts student pass rates by 15% with Microsoft 365 Copilot
Miami Dade College deployed Microsoft 365 Copilot among its President's Cabinet and senior leaders, and used Microsoft Copilot Studio to build AI-powered assistants supporting personalized learning, coding exercises, essay structures and math problems around the clock. In the first semester of implementation in STEM and advanced analytics courses, the college saw a 15% increase in student pass rates and a 12% decrease in dropout rates. A survey found 77% of users completed tasks faster, 76% saw improved work quality, and 81% reported increased productivity; if just 15% of MDC's more than 6,000 employees saved 12 minutes a day, that would total nearly 50,000 hours a year. Encouraged by these results, MDC expanded its Copilot deployment by 400 licenses, prioritizing student-facing employees.
Miami Dade College· United StatesMicrosoft 365 Copilot · Microsoft Copilot Studio · Microsoft Teams +1
Baylor University uses embedded AI to raise payroll data validation efficiency 65%
Baylor University combined Oracle Fusion HCM Analytics with Oracle Payroll Activity Center, using new AI-enabled capabilities as part of its payroll automation transformation. The change delivered a 65% increase in payroll data validation efficiency and a 49% reduction in payroll processing time.
Baylor University· United StatesOracle Fusion HCM Analytics · Oracle Payroll Activity Center · Oracle Fusion Cloud Human Resources +1Harvard Medical School's Walter Lab runs 1.7 million protein interaction predictions using NVIDIA DGX Cloud
The Walter Lab at Harvard Medical School, with access to NVIDIA DGX Cloud through the National Science Foundation's NAIRR pilot program, completed nearly 1.7 million protein-protein interaction predictions on ColabFold in three months using 32-node DGX clusters with 256 A100 GPUs, a task that previously would have taken years. The team curated 40,000 high-confidence protein interactions among 300 human genome maintenance proteins using two custom ML tools (KIRC and SPOC), publishing results via the Predictomes website.
Harvard Medical School (The Walter Lab)· United StatesNVIDIA DGX Cloud · NVIDIA A100 GPUs · AlphaFold +1
Was this helpful?
Your feedback helps us improve our use case database