THE LAST PROMPT ENGINE — TECHNICAL OVERVIEW

The Engine

Name: The Mandate
Brand: Last Prompt

The Last Prompt Engine is the proprietary technology behind The Mandate. It is a decision-intelligence evaluation system that can be wrapped in any thematic skin — survival, corporate, diplomatic, scientific. The same evaluation logic runs in every world.

The engine evaluates the quality of human reasoning under uncertainty. It is content-agnostic, skin-agnostic, and domain-agnostic. The only constant is the rubric.

About the name

A prompt, in its oldest sense, is a nudge — a cue that moves thinking in a new direction without dictating where it lands. In The Mandate, your advisors prompt you. Your questions prompt them. The crisis itself prompts the situation.
But the last prompt — the only input that actually moves the simulation — is yours. The plan you write, in your own words, which a neutral AI then receives and evaluates. We named the engine for that moment: the last word before consequences unfold.
This has no connection to AI prompt engineering, LLM tooling, or anything related to writing prompts for AI systems. The word means what it meant before large language models existed.

Engine Thesis

The scarce skill is no longer information recall.

AI-mediated systems are increasing the complexity of human decision-making at every level. The bottleneck is not access to information — it is the ability to reason structurally under uncertainty.

The Last Prompt Engine is built on a single thesis: better reasoning produces better outcomes. The engine proves this by making the quality of your written plan the direct cause of what happens next in the simulation.

The AI does not drive, decide, or progress the simulation. It only evaluates how well the player thought through the problem.

ENGINE_CORE — EVALUATION_FLOW.pseudo

function evaluatePlan(plan, state) {

// Score against 5-criterion rubric

scores = rubric.evaluate(plan, state);

band = getQualityBand(scores.total);

// Apply interdependency multipliers

deltas = calculateDeltas(band, state);

// Set flags for future crises

flags.update(scores, plan);

return { scores, band, deltas, narrative };

}

// The engine never hardcodes variable names.

// All labels are pulled from the active skin config.

The Decision Loop

Five steps. Every cycle.

The same loop runs in every skin. The context changes. The engine does not.

CRISIS EMERGES

A dynamic event surfaces — shaped by your previous decisions and the current state of your world. No two crises are identical.

CONSULT ADVISORS

Query your team — but they're human. Each advisor sees the world through their own bias, fear, and expertise. Their advice is incomplete by design — not as a trick, but because that is what genuine domain knowledge looks like.

WRITE YOUR PLAN

No menus. No options. You write a free-form strategy in plain English: your goal, your actions, your contingencies, your communication. Your reasoning is the move.

AI EVALUATES

A neutral AI evaluator scores your reasoning quality — not your choices — across six criteria. It runs at temperature 0. It cannot be gamed. It has no pity. It rewards structured thinking.

CONSEQUENCES RESOLVE

The simulation applies outcomes based on how well you reasoned — not what you chose. Poor thinking compounds. Strong thinking builds resilience. The world you face next is the world your reasoning built.

Design Principle

Chronosymbiosis

Most simulations resolve one decision at a time. The Last Prompt Engine does not. The engine is built around a single design principle: your decisions don't vanish after one moment — they resonate forward across time.

Today's trade-offs quietly strengthen or weaken tomorrow's options. Good reasoning compounds into resilience. Flawed reasoning compounds into fragility. The flags, stat deltas, and conditional events aren't mechanical features — they are the engine implementing Chronosymbiosis at a structural level.

Theoretical Foundations

The compounding-consequence structure has a structural parallel in theoretical physics. Observer Patch Holography proposes that reality emerges from overlapping limited observers who must stay consistent where their patches meet.

In The Mandate: advisors are limited-patch observers. The AI evaluator enforces consistency. Outcomes emerge from the quality of the player's synthesis across partial perspectives. This parallel was confirmed by the physicist who developed the framework.

Read the theoretical grounding

The Evaluation Rubric

Six criteria. Zero mercy.

The AI evaluator scores your plan against six criteria, each rated 0–2. The total score (0–12) determines your quality band — and the quality band determines what happens next in the simulation.

A Poor score compounds. A Strong score builds resilience. The simulation does not care about your intentions — only the quality of your reasoning.

POOR

0–4

ADEQUATE

5–8

STRONG

9–12

0–2

Variable Awareness

Does the plan acknowledge the key constraints and trade-offs in play?

0–2

Resource Allocation

Are people, time, and resources specifically assigned — not just mentioned?

0–2

Risk Anticipation

Are second-order effects and contingencies explicitly addressed?

0–2

Communication Clarity

Is there a clear strategy for informing those affected by the decision?

0–2

Multi-Step Planning

Is there a logical sequence with fallback positions if the primary plan fails?

0–2

Temporal Symbiosis

Does the plan consider how this decision connects to earlier choices, or shapes the conditions for future ones?

TOTAL SCORE

Sum of all six criteria — 0 to 12

AI Guardrails

The evaluator cannot be gamed.

Substantial guardrails prevent players from gaming the system, asking for full marks, or exploiting the AI's tendency to be agreeable.

Temperature: 0.0

The evaluator runs at zero temperature. No creative drift. The same plan gets the same score every time.

No Pity Points

The AI must not assume positive outcomes unless the player explicitly describes the mechanism. Vague plans are penalised.

Harsh Interpretation

Plans under 20 words, or lacking contingencies, are immediately penalised. The evaluator is not a cheerleader.

Reasoning Required

Every rubric score must include a reasoning string. The evaluator is accountable for every point it awards or withholds.

Metric Masking

Advisors never reference numeric outcomes. They think in human consequences: 'Morale will shatter' — not '+2 Cohesion'.

Domain Containment

Specialists only see the world through their role. A Security advisor cannot comment on social cohesion. Advice is humanly incomplete by design.

Cognitive Complexity Scaling

Variable count is not cosmetic.

The number of active variables in a skin directly determines the cognitive complexity of the simulation. The engine supports any number.

2–3 Variables

Ethical Compression

Binary trade-offs, moral tension. Fewer variables amplify the emotional weight of each decision.

e.g., Security vs. Compassion

4–6 Variables

Systems Leadership

Interdependency and prioritisation. Decisions ripple across multiple systems simultaneously.

e.g., Colony, Corporate Reckoning

7+ Variables

Executive Strategy

High-complexity environments requiring abstraction, delegation, and long-horizon thinking.

e.g., National Crisis, Diplomatic Simulation

Architecture

Engine vs. Skin

The engine is the unseen hand. The skin is the sensory experience. They are completely decoupled.

LAYER 01

The Engine (System Logic)

Content-agnostic. Never uses the words "Food", "Health", or "Colony". Pulls all labels from the active skin config.

Stat Handler

Manages a dynamic list of variables with min/max clamping and threshold logic. Never hardcodes variable names — reads them from the active skin.

Evaluation Orchestrator

Manages the interface with the AI backend and the 0–10 rubric scoring system. Runs at temperature 0 to ensure deterministic, consistent evaluation.

Rule Engine

A deterministic loop that filters crisis events based on stat thresholds and flags set by previous decisions. Your history shapes what comes next.

Decision Loop

Input → AI Analysis → Outcome Resolution → Next Crisis Selection. The same loop runs in every skin, every cycle.

Memory & Flags

Decisions set hidden flags that persist across cycles. A strong decision in Week 1 can unlock opportunities in Week 3. A poor one can trigger cascading crises.

LAYER 02

The Skin (Thematic Content)

The sensory experience and context. Defined entirely in JSON — swappable without touching engine code.

Thematic Vocabulary

Defines whether the simulation is Colony Survival, Corporate Strategy, or Diplomatic Crisis.

Data Collections

The specific events.json, deltas.json, and narratives.json that populate the world.

Character Profiles

Each advisor has an archetype, core fear, hidden doubt, generational lens, and decision bias weights.

Visual Styles

CSS variables (colours, fonts, layout) that represent the world's atmosphere.

Stat Mapping

Maps generic engine keys (Stat_01, Stat_02) to human-readable labels for the skin's context.

Data-Driven Variable Mapping

ENGINE KEY	COLONY SKIN	CORPORATE SKIN
Stat_01	Sustenance	Cash Flow
Stat_02	Health	Employee Well-Being
Stat_03	Security	Regulatory Compliance
Stat_04	Cohesion	Team Engagement
Stat_05	Infrastructure	Operational Infrastructure
Time_Unit	Week	Quarter
Entity_Name	The Colony	The Enterprise

Collaborators

Have a domain? Build a skin.

The engine is modular. If you work in medicine, diplomacy, urban planning, education, or any field where structured reasoning under uncertainty matters — the Last Prompt Engine can be adapted to your context.

We are looking for collaborators who are frustrated by polarised thinking and inspired by the idea of lateral reasoning as a trainable skill.

Define your variables (2–10+)

Write your crisis events and character profiles

The engine handles evaluation, scoring, and consequence resolution

Academic

Formal architecture paper

“Last Prompt: Operationalising Partial Perspectives in Decision Intelligence Training” — Miranda Kelly and Jonathan Kelly. Working paper, May 2026.

Read on SSRN

See the engine in action.

All three skins are in testing. Apply for beta access above.

Lockwood Colony Corporate