Skip to content
Let's talk

Case study · hero · 2026-05 to present

Kintsu Portal

Simple Cortex built the internal operating platform a new medspa owner needed before opening day: a daily cockpit for decisions, not another admin panel full of settings.

Role
Product and Design Lead, Simple Cortex engagement
Company
Kintsu Medspa
Dates
2026-05 to present
Bucket
current venture
The Kintsu Portal Today cockpit: a Needs your attention panel flagging two required documents to acknowledge, an AI Morning brief summarizing the day, KPI cards reading 69 active services, 66 percent average net margin, 43 services with custom prices, and 0 price mismatches, and a Pricing anomalies panel below
Kintsu Portal · Daily cockpitThe cockpit, not a config screen. The owner opens the portal and sees what needs action today: documents to acknowledge, margins, custom-priced services, price mismatches. The pricing engine runs backstage.

TL;DR

  • Role: Product and Design Lead, Simple Cortex engagement
  • Timeframe: May 2026 to present
  • Business problem: A new practice needed operational clarity before opening, not another admin panel full of settings.
  • What I changed: Simple Cortex delivered an internal operations platform giving the owner a daily cockpit, deterministic pricing, treatment management, and AI support inside a privacy-conscious architecture. I led the engagement and owned product and design end to end.
  • Proof: Blank schema to 15 deployed pages in 72 hours, since grown to 18 operational surfaces. Deterministic pricing across services, tiers, and provider roles. PHI-free architecture enforced in CI. Multi-location access boundaries designed from day one. AI layer bounded by tool contracts that keep financial logic out of the model.

Daily cockpit · action queue

2 points

The Kintsu Portal Today cockpit: a Needs your attention card flagging two required documents to acknowledge, an AI Morning brief, and a KPI row reading 69 active services, 66 percent average net margin, 43 services with custom prices, and 0 price anomalies, each marked Calculated.
01 · Action queue

What needs action today sits above the numbers. Required documents to acknowledge are flagged before anything else, so the owner opens to a decision, not a dashboard.

The cockpit, annotated live. The action queue puts what needs attention today above the numbers, and every KPI is labeled as calculated, not typed.

The problem was not admin

Admin panels show everything. That was the wrong answer.

A first-time practice owner does not need every object in the database exposed as a table. She needs to know what requires attention, what is ready, what could break before opening day, and what is unresolved that a decision could close.

Simple Cortex designed the portal as a cockpit, not a control panel. The system has real complexity: pricing logic, service taxonomy, staff workflows, AI, location controls, compliance, reconciliation. The surface stays calm. The owner should not feel the machinery unless it is asking for a decision.

The product leadership move was choosing that framing first, before a single screen was designed. The pricing engine was the impressive artifact. The cockpit was the right product.

What I did

  • Designed the owner experience around daily operational attention rather than raw configuration. What needs action, what is safe to act on, and what to trust are visible. Everything else is backstage.
  • Built a deterministic pricing model the business could inspect, explain, and trust. Pricing, discounts, commissions, and what-if scenarios route through the engine. The AI layer can explain a margin. It cannot compute one.
  • Created a multi-location architecture with role and access boundaries from day one, before the second location existed.
  • Kept privacy risk low by designing around PHI-free assumptions throughout: aggregate operational signal, no appointment-level records, no guest names. The trust architecture (CI scanning, access controls, deterministic logic) supports the product promise without becoming the headline.
  • Added AI only where it supports decisions without transferring authority from the operator. The assistant answers plain-English questions about the business. It reads bounded functions and explains what the engine already computed.

Scope · Pricing flow

From services overview to deterministic price calculation.

  1. 01 / 03Services grid
    Services grid
    The grid holds the economics. Every service priced across tiers by the deterministic engine.
  2. 02 / 03Service detail
    Service detail
    A single service proves the number: a cost breakdown and a what-if scenario that re-prices every tier live.
  3. 03 / 03Daily cockpit
    Daily cockpit
    The cockpit turns the calculated number into today's decision. One flow, not three disconnected screens.
The Services pricing grid with per-service retail, consumable, labor, and total cost columns plus partner and employee tier prices, several rows carrying custom override badges next to the calculated default price
Deterministic pricing engine · Services gridEvery service priced across tiers by the deterministic engine. Custom overrides layer on top and write to immutable history. This is the surface that moved backstage so the cockpit could lead.

What changed

OPERATIONAL SURFACES · 18 PAGES

The breadth, page by page.

01 / 12
Insights
Memberships
Bundles
Providers
Expenses
Consumables
Compliance
Policies (SOPs)
Reconciliation
Financial reconciliation
Audit digest
Login gate

Insights

The page I check first. Margins, breakeven, and runway in one read, with the money-losing services named instead of buried.

The practice gained an operating surface before opening day. Scattered setup decisions became a visible system: what exists, what needs review, what is safe to act on, what to trust.

  • From spreadsheets to a working operating model: pricing, services, discounts, memberships, consumables, expenses, compliance, and reconciliation in one place.
  • From no daily signal to a cockpit: below-cost services, unsigned attestations, expiring credentials, reconciliation drift, runway, and breakeven surfaced together.
  • From "ask me" to "ask the system": plain-English questions answered against deterministic logic, not model-generated guesses.
  • From single-location assumptions to a multi-location-ready architecture that will not need a rebuild.

The design move was subtraction. The platform does a lot. The interface makes only the right things feel urgent.

The HydraFacial Signature service detail: a cost breakdown of consumable and labor cost totaling 75 dollars, a net margin and discount ladder line, and a what-if pricing scenario with retail, consumable, and labor inputs producing calculated partner and employee tier prices
Pricing engine · Service detailOne service, fully traced. The cost breakdown, the tiered ladder with partner and employee prices calculated rather than typed, and a what-if scenario that re-prices every tier live. The provenance is the product.
The Ask Kintsu chat surface with the question Which services are losing money right now, and a footer note stating every number is worked out by the price calculator and traceable, and that the assistant never makes prices up
AskKintsu · AI layerThe AI layer answers in plain English but never computes money. Every number traces back to the deterministic pricing engine. The assistant explains the business, it does not invent the math.

Reflection

The strongest story here is not "15 pages in 72 hours," or the 18 surfaces it has since become. It is choosing the right surfaces because the owner needed operational confidence, not software theater.