04 / 06From my real operation

Numbers don’t get read. Sentences do.

Owners open a dashboard, see twelve widgets and close it. A summary written in sentences actually gets read.

  • Healthcare context · endocrinology, Miami FL
  • 42 rules · 6 domains
  • Deterministic · no LLM
Dr. Elena Vargas · Endocrinology
Miami, FL · Solo + 1 medical assistant · Monthly snapshot · March 2026
3 active payersChronic-care focus
Scenario toggles

Play with combinations

Auto-generated executive summary
12 of 42 rules triggered

Two critical signals to address this week. Revenue this month is $47k (+11% vs 3-mo avg of $43k), operating margin at 40%, weighted AR at 53 days against your 45-day target.

CriticalB01

BlueShield FL AR at 71 days

$18,300 outstanding, 26 days beyond your 45-day threshold. Trigger collections protocol.

Est. impact: +$18k/mo
CriticalB03

Single payer AR breach (escalation)

BlueShield FL: $18,300 @ 71 days. Escalate to payer relationship manager, not just billing.

WatchB02

Weighted days in AR above target

53 days vs 45-day target. Cash conversion is slow — each extra day of AR is roughly $1,573 stuck in the system.

WatchC02

No-shows spike on Thudays

24% no-show rate vs 14% baseline. Likely a scheduling-friction pattern (end-of-week, after-work) worth investigating.

Est. impact: +$1.1k/mo
WatchE01

BlueShield FL concentration warning

38% of revenue from a single payer (up from ~29% in Q1). Losing them would compress operating margin by roughly 23%.

InsightB06

BlueShield FL dominates accounts receivable

50% of all AR is tied up with BlueShield FL. Their payment cycle effectively sets your cash cycle.

Revenue (mo)
$47k
+11% vs 3mo avg
Op margin
40%
+2pp vs baseline
Slot util
78%
+7pp vs baseline
No-show rate
16%
+2pp vs baseline
Days in AR
53d
+8d vs target
Chronic retention
84%
+6pp vs baseline
Payer breakdown
BlueShield FL
71d · $18k38%
Self-pay
28d · $6.2k25%
Anthem
38d · $9.5k22%
Other payers
45d · $2.8k15%
Revenue · weekly

Last 12 weeks

loading chart…
No-shows · by weekday

Where the friction is

loading chart…
Generated by a deterministic rules engine · no LLM calls · fully client-side42 rules · 5 composable scenarios
How it works

The workflow, and how much of it is built here.

Solid steps run in this sandbox. Dashed steps are what a real implementation adds. Select any step to read what it does.

  • Built in this demo
  • Needed in a real implementation
  • A person decides
  1. 01Data
  2. 02Scenarios
  3. 03Rules engine
  4. 04Summary
Step 1 of 10

Monthly snapshot

Built in this demo

A hardcoded synthetic dataset: one fictional endocrinology practice, one month of operation.

In detail

What it does
  • →Generates an executive summary from 42 rules across six operational domains (revenue, AR, ops, retention, concentration, margin).
  • →Recalculates the summary in real time as you toggle any combination of 5 scenarios — order-independent composition.
  • →Surfaces second-order risks (payer concentration, AR aging) that single-metric dashboards usually miss.
  • →Attaches estimated dollar impact next to each actionable bullet.
How it does it
  • →Hardcoded synthetic dataset (one fictional Miami endocrinology practice, one month).
  • →TypeScript rules engine — each rule has a trigger predicate, severity, narrative template, and optional dollar formula.
  • →Scenario toggles are pure functions that mutate the snapshot; the engine re-runs against the mutated state.
  • →Charts via Recharts, client-only rendering to avoid SSR hydration mismatches.
  • →No LLM calls. No backend. Fully client-side, deterministic, replayable.
What a real impl would need
  • →Live ingestion from a PMS/EHR (DrChrono, Athena, NextGen) and 837/835 claim file parsing for real AR aging.
  • →3–6 months of historical baselines per practice. Without baselines, deltas are meaningless.
  • →Per-practice rule calibration — a solo cardiologist's thresholds aren't a 5-doc OB-GYN group's.
  • →Push delivery layer (email, SMS, Slack) so the summary arrives in the inbox rather than waiting to be pulled.
  • →Audit log + rule versioning so a practice manager can trace why a number flagged six weeks later.
  • →HIPAA-grade infra for US deployment — BAAs with every vendor, encryption at rest, access logs, breach-notification flows.

The pattern transfers cleanly to any ops domain — dental labs, retail, logistics, on-demand services. The work is in the per-domain rule set, not the engine.