EMF: Health Simulator

A plain-English breakdown of the Estuary Mapping Framework. Explore how energy, friction, and organizational momentum shape strategic change.

Work in Progress

Tidal GaugeSLACK WATER

ELI5 / What is going on?

Currently Viewing

What's happening?

Dots are clinicians moving through their workday. They turn purple when clustered, red when stalled. Clinicians drift with the tide (external pressure) but can resist it depending on their state.

Orange circles are burnout thresholds (elastic). Clinicians bounce off these because they represent hard limits. The circles stretch under pressure and snap back, but clinicians avoid entering them entirely.

Green circles are workflow zones (permeable). Clinicians can pass through these with some friction. The Workflow Engine processes and redirects clinicians, helping them move more efficiently through the system.

Yellow circles are tethers. These represent demand constraints like patient volume. Clinicians are tethered because their capacity is bound to these demand nodes. They can only move so far before being pulled back.

Cyan diamonds are constructors (like the Ambient Scribe or Workflow Engine). These actively reduce friction for nearby clinicians, speeding them up or redirecting them away from burnout zones.

Fixed vs moving elements: Constraints and constructors stay in place because they represent stable system structures. Clinicians move with the tide because they're subject to external pressures, while the infrastructure remains fixed.

Arrows show directional influence. When you see arrows pointing from a constraint or constructor, that element is actively pushing clinicians in that direction.

Dashed circles show influence radius. Any clinician inside this radius will be affected by that element, whether attracted, repelled, or slowed down.

Zones affect clinician speed and direction. Each zone type has a different effect: burnout zones repel (clinicians avoid overload), workflow zones slow and redirect (processing takes time), tethers pull back (demand keeps you anchored), and constructors speed up (AI reduces friction).

Energy (X-axis) represents cognitive effort. In the Estuary framework, energy is the "cost" of action. Passing through or near constraints costs energy. High-energy zones (like burnout thresholds) represent high cognitive load, which is why clinicians avoid them. Constructors lower the activation energy required to complete a task.

Time (Y-axis) is a compressed workday. The tide cycle represents a full shift with natural pressure fluctuations. High tide is peak demand (busy period), low tide is recovery time. Watch how clinicians behave differently across the cycle.

What to Watch For

When clinicians turn purple , they're clustering together, mimicking each other's behaviour under stress rather than working independently.

Red dots indicate clinicians who have stalled completely, either burnt out or trapped by competing pressures.

The background tide represents external pressure cycles. High tide brings abundance and flow, low tide creates scarcity and friction.

When a shape pulses and sends a glow to another, that's a signal firing. One element has reached a threshold (like burnout filling up) and is triggering a cascade effect on a connected element.

Key Insight

By placing AI tools strategically near burnout thresholds, you offload cognitive burden before clinicians reach their breaking point. This works because burnout isn't sudden. It builds up as clinicians absorb more friction. Ambient AI intercepts that friction upstream, keeping clinicians in their productive zone.

Clinician

Clinician (clustered)

Clinician (stalled)

Burnout Threshold

Ambient AI

Agent Metrics

Avg Trust100%

Avg Inertia0%

Clustered0

Stalled0

Overview

EMF – Health applies the Estuarine Mapping Framework to healthcare AI strategy. The 2026 healthcare environment faces physical limits: workforce burnout, thick capital cycles, and AI as the key way to scale.

This simulator maps the Energy Cost of Change across four scenarios. It helps strategists find low-energy windows for action and high-energy walls where action creates pushback.

Healthcare Scenarios

Four scenarios represent distinct topological configurations that AI companies must navigate.

Ambient Capacity Restoration

Clinicians are at their breaking point with paperwork. Ambient AI reduces documentation workload so doctors spend less energy taking notes and more time with patients. But if the AI requires too much manual double-checking, clinicians revert straight back to old dictation habits.

if (AI_Active) documentationWorkload -= 25%

Regulatory Phase Shift

Strict regulation (like the EU AI Act) turns loose guidelines into strict law. High-risk AI products without compliance certification hit a brick wall — the energy cost to operate non-compliant tools becomes impossibly high.

if (!certified) deploymentBlocked = true

Reimbursement Tether

Hospitals run on razor-thin margins. AI tools that don’t tie directly to official billing codes (CPT codes) get starved of budget. If a tool doesn’t generate clear reimbursement, adoption drops to zero.

if (!billingCodeAttached) hospitalAdoption = 0

Confident Hallucination

When an AI model makes a confident clinical mistake, trust plummets instantly. Rebuilding clinical trust takes months of flawless performance. A single high-profile error traps the product in a liability risk zone.

TrustLostInSeconds != TrustRebuiltOverMonths

Healthcare Constructors

Constructors transform input states to output states without undergoing net change themselves.

Constructor	Function	Scenario
Ambient Scribe	Reduces cognitive friction by transforming conversation → SOAP note	Ambient Capacity
Compliance Audit	Enables crossing regulatory walls via audit trail	Regulatory Phase Shift
CPT Enabler	Extends revenue tether radius via new billing codes	Reimbursement Tether
Trust Anchor	Slows trust decay, aids linear recovery via verification	Hallucination Event

Analysis Tools New

These buttons add overlays to help you understand what’s happening in the simulation.

Cynefin Overlay

The Cynefin framework helps you understand how predictable different parts of the system are. When you click Cynefin, the simulation area gets colour-coded into four zones:

Clear (Green): These areas are predictable. Cause and effect are obvious. Best practices work here. Think of well-documented procedures that always give the same result.
Complicated (Blue): Still predictable, but you need expertise to understand what’s going on. An expert can analyse the situation and figure out the right approach. Think of a specialist diagnosing a known problem.
Complex (Purple): Cause and effect only make sense in hindsight. You can’t predict outcomes because too many things interact. The best approach is to try small experiments and see what happens.
Chaotic (Red): No clear cause and effect. Things are unstable and you need to act first, then figure out what’s happening. Think of a crisis where you stabilise first and ask questions later.

The simulation calculates which zone each area belongs to based on two factors: how volatile the area is (the right edge is more volatile), and how close to constraints an area is (more constraints means more structure).

Network Topology

Click Net to see the invisible relationships between agents. The simulation draws purple lines between agents that are close enough to influence each other.

This shows you the social network forming in real-time. Agents that are near each other can share information and copy each other’s behaviour. The lines get stronger (more visible) when agents are closer together.

You can use this to spot clusters forming, identify isolated agents, and see how information might spread through the group. The total number of connections is shown at the bottom of the screen.

Wardley Map

Click Wardley to overlay strategic positioning axes onto the simulation.

Wardley Mapping is a strategy tool that plots components based on how evolved they are and how visible they are to users. The overlay adds:

X-Axis (Evolution): Shows how mature something is. The left side is “Genesis” (new, experimental ideas). Moving right, you pass through “Custom Built” (one-off solutions), then “Product” (off-the-shelf options), and finally “Commodity” on the far right (utilities everyone uses like electricity).
Y-Axis (Visibility): Shows how visible a component is to end users. Things at the top are user-facing and obvious. Things at the bottom are invisible infrastructure that users never see.

The labels change depending on which scenario you’re viewing. In healthcare scenarios, the evolution stages might be labelled differently to match the domain (for example, “Research” to “Standard of Care”).

This overlay helps you think strategically about where things are positioned. Volatile areas (left side) suit experimental work. Stable areas (right side) suit commodity services.

VSM Roles (Viable System Model)

Click VSM to see how the simulation maps to Stafford Beer’s Viable System Model, a way of understanding organisations as living systems.

The overlay highlights four levels:

System 1 Operations (Green): The agents themselves. These are the things that actually do the work. In an organisation, this would be the front-line teams delivering products or services.
System 2 Coordination (Yellow): The constraints. These dampen oscillations and stop parts of the system from fighting each other. They’re the rules, schedules, and standards that keep things running smoothly.
System 3 Control (Blue): The constructors. These allocate resources and monitor performance. They make sure the operational units have what they need and are working effectively.
System 5 Policy (Red): The boundary of the entire system. This is identity and purpose. It defines what the system is and what it’s not. The red border around the simulation area represents this.

This overlay helps you think about organisational design. A viable system needs all five levels working together. If you only have operations (System 1) without coordination (System 2), you get chaos. If you have too much control (System 3) without operational freedom, you get stagnation.

Alternative Frameworks

The current implementation is primarily Agent-Based Modelling (ABM) with continuous physics. These enhancements map organizational complexity theories to specific simulation mechanics.

Multi-Level Selection (Wilson & Wilson, 2007)

Agents form groups that compete as units, creating selection pressure at both individual and group levels.

Mapping: Teams compete for resources; successful team patterns propagate.

Network Topology (Barabási, 2002)

Replaces spatial proximity with network connections using power-law degree distributions for realistic organizational structure.

Mapping: Influence flows through hierarchy and established links, not just physical proximity.

Evolutionary Strategies (Axelrod, 1984)

Agents carry strategy genotypes subject to mutation, crossover, and selection.

Mapping: Organizational practices evolve through competitive mimicry (see Institutional Isomorphism).

Healthcare Physics

Constraints modify the energy required to move actants through the healthcare terrain.

Elastic Constraint (Burnout)

Modeled using Hooke’s Law with a failure point. When cognitive load exceeds the yield point, the workforce snaps back.

E_{elastic} = \frac{1}{2} k x^2 \quad \text{where } x = \text{Cognitive Load}

Rigid Constraint (Compliance Wall)

Step function where energy approaches infinity for non-compliant actors.

E_{rigid}(x) = \begin{cases} 0 & \text{if } x \in \text{Compliance} \\ \infty & \text{if } x \notin \text{Compliance} \end{cases}

Tether Constraint (Revenue Radius)

Cost is zero inside CPT code scope, infinite outside.

E_{tether}(d) = \begin{cases} 0 & d \le r \\ \infty & d > r \end{cases} \quad \text{where } r = \text{CPT scope}

Hysteresis (Trust Dynamics)

Trust decays exponentially after errors but recovers linearly, requiring far more work to rebuild.

\text{Decay: } T \sim e^{-kt} \quad | \quad \text{Recovery: } T \sim +1/t

Advanced Physics Unique to Health Sim

This simulator introduces two physics models not present in the standard Estuarine Mapping sims, designed specifically for modelling healthcare trust dynamics and volatile zone behaviour.

Langevin Equation (Brownian Motion)

In the volatile zone (right edge), agents follow the Langevin equation (a stochastic differential equation that models proper Brownian diffusion rather than uniform noise).

dx_t = -\nabla V(x_t)dt + \sigma \, dW_t

Where ∇V is the energy gradient (gradient descent toward lower energy), and σdW is Gaussian noise from a Wiener process.

Other EMF Sims

Uniform random jitter: agents move jerkily like “TV static”

Health Sim

Gaussian random walks: agents drift smoothly like “smoke diffusing”

Used in: All scenarios (volatile zone behaviour)

Hysteresis Effect (Asymmetric Energy)

Trust dynamics follow a hysteresis loop where falling into a liability well is fast but climbing out is slow. This models the asymmetric energy cost of reputation damage.

E_{recovery} \gg E_{loss} \quad \text{(25} \times \text{ asymmetry)}

Trust Decay (Fast)

Exponential: T *= exp(-0.05)

~40 frames to collapse

Trust Recovery (Slow)

Linear: T += 0.002

~500 frames to recover

Visual feedback:

Red pulsing glow: agents losing trust (inside dark constraint)
Teal pulsing glow: agents recovering trust (climbing out)
Agent colour shifts toward red as trust drops

Used in: Confident Hallucination scenario (dark constraints)

System Dynamics & Models

Visualising the feedback loops and hierarchical structures driving the simulation.

Agent Dynamics (Boids + Behavioural Econ)

How agents make decisions: combining flocking rules with cognitive biases under constraints.

Environment

Agent Decision Core

Output

Neighbors

Constraints

Strategic Vectors

Boids Rules

Physics Engine

Cognitive Bias

Velocity Update

State Change

Viable System Model (VSM) Mapping

Mapping Estuarine entities to Stafford Beer’s cybernetic tiers.

System 5

Policy

Rules & Boundaries

System 4

Intelligence

Strategic Vectors

System 3

Control

Constructors

System 2

Coordination

Constraints

System 1

Operations

Agents

Burnout Causal Loop Diagram

The reinforcing cycle of burnout and the balancing loop of Ambient AI.

Workload

Stress

Burnout

Capacity

Error Rate

Ambient AI

Constraints Reference

Type	Metaphor	Dynamics
Elastic	Rubber Band	Stretches with pressure, snaps back at yield point (Burnout).
Rigid	Concrete Wall	Fixed boundary. Infinite energy cost to cross (Compliance).
Permeable	Mesh Fence	Passable with friction. Filters agents by cost (Workflow).
Tether	Dog Leash	Zero cost within radius, infinite outside (Reimbursement).
Dark	Gravity Well	Attracts agents. Easy to enter, hard to leave (Liability).