5 systems One per level of care, none connected
Independent living, assisted living and memory care each end up on a different platform. Nobody has a resident's whole picture.
Healthcare
You are running five different systems across your continuum, and none of them talk.
Operators say it themselves: integration is the problem, not the number of devices.
Book a 20-minute call Free. No demo, no slides.
1 in 4
US adults aged 65 and over report falling each year, and falls are the leading cause of injury death for that group.
What is happening
Five systems across one continuum, and a resident who moves between all of them.
>$50B Annual US medical spend on falls
One prevented fall pays for a year of monitoring across a wing. In memory care the average fall costs $9,300, up 77% since 2022.
93% Already use fall detection or cameras
Adoption is not the gap. The devices are in the building. The data from them is not anywhere a manager can act on it.
Regulatory scrutiny is rising
CMS has tightened guidance on resident care and fall risk, and underwriters are asking harder questions. Evidence that a check happened matters as much as the check.
Intelligence, plumbed in
Nurse call logs and care notes together predict tonight's risk.
The build is a panel connector, one resident identity across five systems, and a test against incidents you already had.
How we make AI survive real data-
Connectors -
A semantic layer -
Evals you can check
What changes
Judge us on this, not on what we built.
One picture Every device reporting into one operational view
Nurse call, fall detection, wearables, door and bed sensors normalised into one event stream, next to census and care plans.
Earlier signal Change detected before it becomes an incident
Patterns across devices that no single vendor's dashboard can see, because no single vendor has the other four feeds.
Evidence Proof that a check happened, with a timestamp
For the family conversation, the survey, and the insurer.
Research
We wrote a full page on each of these, with the sources.
Each one carries its own figures and the citations behind them. Start with whichever sounds most like your week.
United States
One in four residents falls each year, and the warning was in the logs
Falls are the leading cause of injury death for people over 65. The signals that precede one are already being recorded, in systems that do not talk.
United StatesNobody wants a sixth dashboard
The sensors work. The problem is that each one arrived with its own screen.
However hard, whatever it is
Five systems is one example. Bring the one that worries you at night.
This page is about one resident record. If yours is occupancy, agency cover or an incident nobody saw coming, we start the same way.
-
01 We sit with you
Days where the work happens, not a workshop in a meeting room. We watch the job get done and write down the shortcuts nobody wrote down.
-
02 We read everything
Your data, your rules, your vendors and their documentation, and the published research on your sector. We report what is actually in there.
-
03 We break it to first principles
Not which tool fixes this. What is actually causing it, taken apart until we reach the piece that cannot be divided further.
-
04 Then we build
Weeks, not quarters. By this point we are not guessing what to build, and guessing is the thing that makes projects long.
Where we sit
Your clinical system stays. Your property ledger stays. We build the one resident record.
4
What you get
- One picture Every device reporting into one operational view
- Earlier signal Change detected before it becomes an incident
- Evidence Proof that a check happened, with a timestamp
3
Built new for you — none of this exists in your stack today
- A wearable call button that works in the garden too
- A move-in that happens once instead of five times
- A floor screen showing the risks for tonight
2
The resident layer Reads your clinical and property systems. Writes into no chart unapproved.
Connectors, one agreed meaning per field, and a model reading what no
field holds. Accuracy measured on your own records.
1
- PointClickCare
- Yardi Senior Living
- MatrixCare
- Nurse call systems
- CarePredict
What you already run — unchanged, and still yours
If a device or a chart records it, we can reach it. A nurse call panel, a clinical system with no API, a property ledger. All of it can be joined.
-
No API -
No documentation -
A terminal from 1994 -
It arrives as paper -
The vendor said no -
It reports nothing
Not a list of limits. Name yours on the call.
And once we can reach it, a model can read it. Most of the value here is in the sources nobody ever structured — the note, the letter, the screen.
Who this is for
The people who feel this first
-
Executive Director -
VP of Operations -
Director of Health & Wellness -
Risk Manager -
Owner / Operator
Straight answers
The questions you would ask on the call
-
Do you sell sensors?
No, deliberately. You already have devices. What you do not have is a layer they all report into. We build that, which means every sensor vendor becomes a partner rather than something you have to rip out.
-
Is this a medical device? Does it need FDA clearance?
Not as we build it. We report what happened: a resident has not moved in 40 minutes, a door opened at 2am. We leave the clinical judgement to your clinicians. That line is what keeps it a wellness product rather than a regulated device. We hold to it in the software and in what we claim.
-
What about residents' privacy?
Event data is minimised by design and access is role-scoped and logged. Where inference is useful, we prefer to run it on the device so that raw audio or video never leaves the building.
-
Can AI predict risk from nurse call logs?
Joined with the care notes, yes. We test the picture against incidents you already had. The night staff see a floor screen, not a report.
Also in healthcare
Healthcare
Skilled nursing & post-acute care
Your team is not wrong about the denials. They just do not have four hours per appeal to prove it.
HealthcareHospitals & health systems
Denials are not a billing problem. They are a documentation problem that surfaces as a billing problem.
HealthcarePhysician groups & clinics
Ninety-two percent of practices have hired or reassigned staff purely to keep up with it.
Next step
Start with your own numbers.
-
We talk
20 minutes. Free.
You tell us what is not working. We ask how the work really gets done.
-
We look at your data
A few weeks.
We read your systems, including the notes and letters no field holds. You get what is really in there, what it costs, and the accuracy we can hit.
-
We build
A few months.
Only if step 2 says it is worth it. Fixed price, agreed before we start.