Work Connect
Healthcare shift marketplace · 2026
A product that fills a hospital's open nursing shifts, working inside the scheduling tool its staff already use. I co-lead development of the app used by the hospital's scheduling staff.
- The problem
- When a nurse calls in sick, covering the shift is slow and expensive.
- What I did
- I co-lead the app, wrote the shift-fill agent's requirements, and built its logic and evaluations.
- The result
- An automated product that manages a hospital's nursing shifts.
A nurse calls in sick, and the shift has to be covered within hours
When a nurse calls in sick, someone has to cover that shift fast, and the usual options are slow and expensive: a round of phone calls, or an outside agency charging a premium. Work Connect spots the gap the moment it opens, gives the facility a window to fill it internally, and only then offers a way to reach outside.
I co-lead the app used to manage shifts
I co-lead the app used by scheduling staff to see open shifts, incoming workers and coverage reports. I wrote many of its requirements, which guide our AI development: if the code contradicts them, we correct the code. The app and a separate backend share a database, so I also help keep their schemas aligned. I was the first on this project to work this way, directing AI from written requirements.
Documents come first, then the AI writes the code.
In this project the documents come first. Before anything gets built there is a product specification, a requirements document per feature with its acceptance criteria, a technical blueprint, the work orders that split it into units, and the interface design. The AI turns those documents into code, and I review three things: the documents, the output and the tests. On one feature the AI ignored the plan and rebuilt the duplicate that plan existed to prevent, so I threw the work away and replanned it.
AI agents help hospitals fill open nursing shifts.
Covering an open shift by hand is seven steps: notice the gap, apply the agreed rate, send the request to an outside supplier, review the candidates who apply, book one, write the booking back into the scheduling tool, and tell the manager. A team of six specialized agents takes those steps over, including phone calls that chase a credential missing before a shift starts and outreach messages drafted for a person to send. Some agents accept rules written by hospital staff in plain language.
Hospitals approve automation rules before activating them.
The agents start paused. For those that accept delegated rules, a coordinator writes the rule in plain language and confirms the system's interpretation before it takes effect. If the shift-fill agent encounters ambiguity, it returns the shift to the manual queue instead of taking external action. Runs are logged, and I evaluate its rule interpretation against real cases before choosing a model.
Shift coverage, reporting and support for multiple facilities
I built reporting that lets scheduling staff compare facilities, and support for customers with multiple facilities across states, including facility selection, settings and rates. I also worked on sign-in across customers, with permissions checked on each page request, and configurable components that can serve another industry. I built the first version of the worker outreach agent; the team has developed it further since.
I can put automation inside a workflow where a mistake has a real cost, by giving every step a limit, a human confirmation and a record of what it did.