This AI Fills Healthcare Shifts in Minutes

Home healthcare is breaking.

Staffing shortages, last-minute cancellations, credential checks, compliance requirements, and manual scheduling are overwhelming care teams and putting patient outcomes at risk.

In this episode of Built This Week, Sam Nadler and Jordan Metzner sit down with Arya Health leadership to see how AI is already replacing hours of manual healthcare operations with real production systems.

Arya Health uses AI to instantly match patients with the right caregivers based on credentials, availability, location, eligibility scoring, and compliance rules all while remaining fully HIPAA compliant.

In the episode, we walk through:
• How AI turns messy hospital discharge summaries into actionable start of care workflows
• How caregivers are matched and notified automatically
• Why Arya reframed “shifts” as patients and how that changed everything
• How AI fills urgent care gaps in minutes instead of hours
• The real security architecture behind HIPAA compliant AI
• Why Arya forbids long term AI memory by design
• How multi cloud AI works across AWS and Google safely
• What happens when AI costs suddenly spike in production
• Why scheduling healthcare looks like the traveling salesman problem with time windows

This is not a demo.
This is what AI looks like in production healthcare today.

(0:00) This AI fills healthcare shifts in minutes
(0:38) Welcome to Built This Week
(1:07) Introducing Arya Health leadership
(1:42) What Arya Health actually does
(2:37) AI generated start of care workflows
(3:28) Turning discharge notes into care plans
(4:21) Matching patients with caregivers
(5:12) Automated outreach and workflow actions
(6:02) Leadership reacts to the AI workflow
(7:15) How non experts prototype healthcare AI
(8:50) Why demos and real healthcare are different
(9:19) HIPAA compliance and security realities
(10:19) Multi cloud AI architecture explained
(11:15) Using AWS Bedrock and Google Vertex AI
(12:06) Why only approved cloud models are allowed
(13:30) Secure AWS and GCP data isolation
(14:26) When AI costs unexpectedly spike
(15:12) Single shot prompting in production
(17:21) Why Arya blocks long term AI memory
(18:01) Controlling AI with typed inputs
(20:01) Real world impact and metrics
(20:26) Replacing hours of manual scheduling
(21:51) Filling urgent shifts instantly
(22:45) Improving care quality through consistency
(23:22) Reframing shifts as patients
(24:05) Building care teams not schedules
(24:32) Eligibility scoring and heuristics
(25:52) Ranking caregivers by fit
(26:13) Optimizing routes and schedules
(27:34) Industry news discussion
(39:36) Final thoughts and wrap up

🔗 LINKS

Arya Health
https://www.aryahealth.ai/

Built This Week
New episodes every Friday

👤 HOSTS

Jordan Metzner
https://linkedin.com/in/jordanmetzner

https://x.com/mrjmetz

Sam Nadler
https://linkedin.com/in/sam-nadler-1881b75

https://x.com/Gravino05