AI Risk Flagging of NDIS Shift Notes

Industry: Disability support services, NDIS
Organisation: Australian NDIS registered provider
Solution type: AI enabled operations platform with third party integration
Core technology: Azure OpenAI, Azure AI Search, .NET, Angular, SQL Server, Deputy API
Engagement: Analysis, design, integration, build and testing

Headline resultTens of thousands of shift notes risk rated, with high risk notes surfaced to coordinators first

Overview

NDIS support workers write hundreds of shift notes every week. Hidden among them can be a missed medication, a safety concern or a change in a participant’s wellbeing. We built a platform, using our AI software development services, that syncs data from Deputy and uses AI to rate every shift note as low, medium or high risk, so coordinators can act on what matters first.

The Business Problem

Shift notes were stored in the rostering system and read in the order they were written. Important information could easily be missed in routine paperwork, and there was no efficient way to know which notes needed urgent attention. The provider also lacked a central place for staff and participant records, admin notes and files.

High note volumeHigh volumes of free text shift notes
Manual risk checksRisk identification depended on someone reading every note
No central recordNo central record for participants, staff and documents
Keep DeputyA need to keep Deputy as the rostering system

Our Solution

We built a custom platform using .NET microservices, Angular and SQL Server on Azure. Staff, participant and shift data, including notes and kilometres travelled, syncs from Deputy every few minutes into the provider’s own database. Every note then passes through an AI review using Azure OpenAI Service and Azure AI Search, which assigns a low, medium or high risk rating.

Coordinators sort and filter by risk rather than date. Administrators can define what the AI should treat as high risk without code changes. The platform also stores context notes and tagged, searchable files against staff, participants and individual shifts. Access is through single sign on with the provider’s company domain.

Deputy syncs every few minutes
AI rates each shift note
Notes sorted by risk level
Coordinators review high risk first
Context and files stored centrally

NDIS shift note platform with AI risk flagging and Deputy integration

Key Features

Scheduled sync of staff, participants, shifts and notes from Deputy
AI risk rating of every shift note
Coordinator view sorted by risk level
Admin control of high risk criteria without development
Context notes on staff, participants and shifts
File upload, tagging and document search
Full audit trail of AI reviews
Single sign on with invitation only admin access

Outcomes

Tens of thousands of shift notes reviewed and risk rated automatically
A small proportion of high risk notes surfaced for immediate coordinator attention
Thousands of timesheets synced without manual handling
Deputy retained as the rostering system, so support workers kept their existing workflow
Delivered on time and within budget

Technology Stack

Frontend4 technologies

Angular

HTML

CSS

JavaScript

Backend5 technologies

.NET

REST APIs

Entity Framework

Microservices

Database1 technology

SQL Server

AI2 technologies

Azure OpenAI Service

Azure AI Search

Cloud and DevOps4 technologies

Azure Web Apps

Azure API Management

Azure Blob Storage

Azure DevOps

Integration1 technology

Deputy

Who This Solution Suits

This approach suits NDIS providers, home care and aged care operators, community services organisations and any business where frontline staff write case notes that may contain safety or compliance risks.