Use Case Intelligence RSS Search use cases Search
Microsoft Healthcare United States

Providence

Customer Service Automation · Document Processing

With the ever-growing popularity of electronic messaging between patients and caregivers, US healthcare organization Providence faced a deluge of incoming messages. This flood required triage and interfered with the time providers needed to spend with their patients. Providence clinicians, informaticists, and AI specialists developed a new product, ProvARIA, based on Azure OpenAI Service.

Read the original story Explore all use cases
In December of 2022, electronic communications surpassed phone calls as the primary means of communication between patients and providers.
Providence medical assistants, with support from ProvARIA, are now processing 5,000 messages per day, covering 145 Providence clinics and 650 providers.
Taking advantage of the flexibility and familiarity of communications available 24/7 using mobile apps and/or email, patients no longer need to wait for office hours to check in with their healthcare providers.
The number of patient messages had increased threefold since the start of the COVID-19 pandemic.

Reported impact

Business outcome

Best of all, patients, especially those with concerning symptoms, are experiencing faster turnaround times. That means more same-day consultations and/or appointments for urgent issues,” says Parsons. ProvARIA empowers caregivers to respond more quickly and accurately and frees up time for them to do what they do best—provide personalized, face-to-face care to patients in need.

  • Customer Experience
  • Productivity Improvement
  • Risk Reduction
  • Scalability

Solution

Providence built this solution on Azure OpenAI Service. With the ever-growing popularity of electronic messaging between patients and caregivers, US healthcare organization Providence faced a deluge of incoming messages. Azure OpenAI Service provides the generative AI model layer used for summarization, drafting, classification, or copilots in the workflow. It was important to find a solution that meshed with the way Providence caregivers work, rather than creating a new set of tools that would require separate access and training. As third-party solutions did not fulfill that requirement, a team of Providence clinicians, informaticists, and AI specialists developed a new product, ProvARIA, based on Azure OpenAI Service. Messages, calls, or requests enter the existing workflow, Azure OpenAI Service classifies or summarizes them, and the reviewed output is surfaced to care teams inside the EHR workflow.

Data flow

Messages, calls, or requests enter the existing workflow, Azure OpenAI Service classifies or summarizes them, and the reviewed output is surfaced to care teams inside the EHR workflow.

Solution architecture

1 components · 1 layer
  1. Compute
    • Azure OpenAI Service Provides the generative AI model layer used for summarization, drafting, classification, or copilots in the workflow.

Architecture clues

  • The AI workflow is wrapped with rules-based verification and guardrails.
  • The user experience is embedded directly in the EHR workflow.

Evidence from the source

Best of all, patients, especially those with concerning symptoms, are experiencing faster turnaround times. That means more same-day consultations and/or appointments for urgent issues,” says Parsons.
Taking advantage of the flexibility and familiarity of communications available 24/7 using mobile apps and/or email, patients no longer need to wait for office hours to check in with their healthcare providers.
The number of patient messages had increased threefold since the start of the COVID-19 pandemic.
With the ever-growing popularity of electronic messaging between patients and caregivers, US healthcare organization Providence faced a deluge of incoming messages.
Transparency Evidence & methodology 100/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    5 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    4 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Microsoft

    Providence customer story

    First-party
    https://www.microsoft.com/en/customers/story/1701699654934326459-providence-azure-openai-service-united-states
    Source type
    Vendor-published customer story
    Published
    Nov 10, 2023
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Nov 10, 2023 · Microsoft · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Microsoft Feb 5, 2025 Vodafone Telecommunications Global In the face of rising customer demand for new digital services, global telecommunications provider Vodafone is exploring innovative ways to enhance the customer experience, including better handling of complex inquiries… Africa, Vodafone serves more than 330 million customers in 15 countries Customer Service AutomationDocument Processing Azure AI Foundry · Azure AI Search · Azure AI Services Microsoft Jan 28, 2025 U.S. Venture Financial Services United States U.S. AutoForce pays thousands of invoices per day and 50% of orders are for same day delivery. Its legacy supply chain and warehouse management tools could no longer reliably perform at this volume and the finance team… A difference on day one with Microsoft 365 Copilot for Finance Customer Service AutomationDocument Processing Dynamics 365 Finance · Microsoft 365 · Microsoft 365 Copilot Microsoft Dec 9, 2024 Hellenic Cadastre Public Sector Greece Hellenic Cadastre, responsible for Greece's property records, faced delays and inefficiencies as property transactions required manual processing of paper documents, leaving some citizens waiting months or even years to… The system also tracks the cost per assessment. "Right now, the cost of each contract assessment is 0.11 euros,… Customer Service AutomationDocument Processing Azure OpenAI Service · Power BI