Every handoff,
ranked and owned.
Signals reads your chart, your roster, and ten public federal datasets in one query. It finds the dollar-valued work sitting between your clinical, billing, and staffing teams, and routes each item to the one person who can close it.
- Deploy in
- 14 days
- SOC 2 + HIPAA
- Ready on day one
- Read-only on your EHR
- No write-back required
One point below NC tier. A missed diagnosis in the chart would tip her over.
A resident starts IV antibiotics on a Tuesday. The clinical team does everything right. The facility loses $5,000 to $10,000 over the next three weeks.
The clinical team and the billing team don't share a chart. They don't share a meeting. They barely share a hallway. The dollar-valued handoff never happens.
Orders, eMAR, MDS, diagnoses. The clinical team is doing its job. Every dose is logged.
The same resident is being billed at $260/day Medicaid when the IV antibiotic qualifies them for $500+ Part A.
Clinical sees the chart. Billing sees the claims. Neither sees the other. The $5,000 leaves the building quietly.
That handoff has an owner somewhere. Signals scores the owner, routes the ticket, and verifies the fix. Every handoff, every day.
A rules engine that proposes and retires its own rules.
Five steps, on repeat, without anyone asking. Every step is auditable. Every finding traces back to the rows that triggered it.
A real operator works 20 to 40 items at a time. Show them 400 and the feature doesn't work.
Every pattern gets a turn. One big compliance finding can't saturate the queue.
- Ingest01
Residents, orders, MDS, eMAR, labs, staffing, claims.
- Detect02
The catalog runs against every row, every night.
- Rank03
Dollar value, urgency, and round-robin balance.
- Route04
Into one person's queue, with a draft action attached.
- Learn05
The engine grades itself and tunes what fires next.
The engine proposes new detection patterns on its own.
Four statistical passes run against your operational graph every night. When one spots something, a proposer drafts a new detection pattern and ships it as data. No code deploy.
A facility's number on a metric is far enough from the chain median to be suspicious. Robust outlier math, not a trigger-happy z-score.
Residents with feature pattern X have adverse event Y happen at materially higher rates than the base population.
Event A tends to be followed by event B inside a bounded window. Lead indicator, not coincidence.
A facility's own metric diverges from its recent history and the chain trend. Something changed here, and only here.
Five categories. One queue.
Every finding arrives with a dollar value, an expiration, and a chain of evidence pointing back to the row that triggered it.
Thirty minutes. Your employees. Your vendors.
We walk your actual staff roster and vendor list, show what HQ would look like across your portfolio, and let you drill into the evidence behind any score. You'll know by the end whether this fits your chain. No slide deck.