My role
Forward Deployed Product Designer and Engineer
Company
Foxcommand.ai
Scope
AI-assisted Hospital Incident Intake
Hospitals manage incidents every day, from medication errors and equipment failures to workplace violence.
Health systems need to identify what happened, investigate it, coordinate the right response, and prevent the same problem from happening again.
As part of an AI enablement engagement with an Upstate New York health network, I led the product strategy, design, and development of an AI-assisted incident management system.
The goal: identify high-priority incidents faster, reduce investigator workload, and improve patient and workplace safety.
I began by working closely with Patient Safety Operations, and Incident Investigators to map out the entire workflow from initial incident submission to final reporting and handoff to claims or escalation to VP review.
I studied how the work actually happened, where cases stalled, and why investigators were overwhelmed. This required a systems-thinking view of the entire process. I found a process that was slow and heavily manual.
After examining the full process, I chose initial intake as the first place to apply AI.
Every incident passes through intake. It is also where the person closest to the event still has the clearest context. Once an incomplete or unclear report enters the system, every later step becomes harder. Investigators must reconstruct what happened, determine urgency, find the right people, and decide where the case belongs.
Starting later in the process would mean repairing poor information after context had already been lost. I chose to improve the information at its source.
My strategy was to help employees report incidents clearly and help investigators understand them earlier. This could reduce manual work and support better prioritization, coordination, and prevention without requiring the hospital to replace its entire process at once.
AI turns the employee’s incident description into a structured draft, but the employee reviews and corrects it before submission. Investigators remain fully in control for the investigation and any action taken.
The trade-off: requiring review adds a step and limits full automation, but prevents an incorrect AI interpretation from becoming part of the official record.
The design allows anyone to submit an incident report anonymously, in line with legal requirements.
Sensitive information is captured separately and kept out of the AI workflow. The system uses local or approved models so protected health information stays within the hospital’s system.
Checks keep the model on task to prevent hacking or prompt injections.
The trade-off: employees enter slightly more information upfront, but the system remains safe and in line with legal requirements.
Thinking beyond demo happy paths
If the AI fails or becomes unavailable, the incident can still be submitted and the investigation can begin.
The trade-off: No retry option may feel less agentic, but failing AI should never prevent someone from reporting a safety incident.
Complexity needs to earn its place.
Not every product requires several LLM agents.
The workflow didn’t need an autonomous agent. AI could create more value by reading each report once, organizing the key information, and preparing it for human review.
The trade-off: The experience makes for a less flashy demo, but it is faster, cheaper, more reliable, and more realistic to operate at scale.