LAST PROMPT ENGINE — DECISION INTELLIGENCE SYSTEM

The engine that
evaluates how you think

Not what you choose. How you reason.

Last Prompt is a decision-intelligence engine that places you inside a crisis, gives you biased advisors with hidden agendas, and asks you to write your plan in free text. A neutral AI then evaluates the quality of your thinking — and the simulation resolves accordingly.

You are not just solving problems. You are navigating perspectives.

A reflective leadership simulation about making decisions under pressure, navigating expert bias, and learning how your reasoning shapes outcomes.

LAST_PROMPT_ENGINE — EVALUATION_RESULT.json
"quality_band": "STRONG",
"total_score": 9 / 10,
"variable_awareness": 2 — "Acknowledged all five constraints and their interdependencies."
"risk_anticipation": 2 — "Contingencies for both hostile and sick scenarios are explicit."
"narrative_outcome": "The colony gains an asset. Morale improves."
The Core Idea

AI-mediated complexity has made structured reasoning the scarcest skill.

The world doesn't lack information. It lacks people who can reason clearly under uncertainty — who can identify trade-offs, anticipate second-order effects, and communicate intent when everything is on fire.

Last Prompt is a decision-intelligence engine built to develop exactly that skill. It doesn't reward the right answer. It rewards the quality of your thinking.

Read the engine spec

One engine. Infinite worlds.

The Last Prompt Engine is content-agnostic. The same evaluation logic powers a post-collapse colony, a corporate crisis, and an off-world settlement. Swap the skin, keep the intelligence.

The AI cannot be gamed.

The evaluator runs at temperature 0. It has no pity. It penalises short plans, vague contingencies, and ignored constraints. You cannot ask it for full marks.

Advisors with real psychology.

Every character has an archetype, a core fear, a hidden doubt, and a generational lens. Their advice is humanly incomplete — by design.

The Decision Loop

Five steps. Every cycle.

The same loop runs in every skin. The context changes. The engine doesn't.

01

CRISIS EMERGES

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

02

CONSULT ADVISORS

Query your team — but they're human. Each advisor sees the world through their own bias, fear, and generational lens. Their advice is incomplete by design.

03

WRITE YOUR PLAN

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

04

AI EVALUATES

A neutral AI evaluator scores your reasoning quality — not your choices. It cannot be gamed. It has no pity. It rewards structured thinking.

05

CONSEQUENCES RESOLVE

The simulation applies outcomes based on how well you reasoned — not what you chose. Poor thinking compounds. Strong thinking builds resilience.

The Evaluation Rubric

Five criteria. Zero mercy.

The AI Evaluator scores your plan against five criteria, each rated 0–2. The total score (0–10) 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 doesn't care about your intentions — only the quality of your reasoning.

POOR
0–3
ADEQUATE
4–7
STRONG
8–10
0–2
Variable Awareness
Does the plan acknowledge the key constraints and trade-offs?
0–2
Resource Allocation
Are people, time, and resources specifically assigned?
0–2
Risk Anticipation
Are second-order effects and contingencies addressed?
0–2
Communication Clarity
Is there a clear strategy for informing those affected?
0–2
Multi-Step Planning
Is there a logical sequence with fallback positions?
TOTAL SCORE
Sum of all five criteria — 0 to 10
Who Is This For

Three audiences. One engine.

PLAYERS

Strategy gamers who want to think, not click.

If you're frustrated by games that reward memorisation over reasoning, Last Prompt was built for you. Your plan is the move. Your thinking is the mechanic.

Explore Colony
ORGANISATIONS

Leadership development that isn't a PowerPoint.

Deploy Corporate Reckoning as a training tool for senior leaders. The AI evaluator provides 1:1 feedback on reasoning quality — not personality types or team roles.

Explore Corporate
COLLABORATORS

Build a skin for your world.

The engine is modular. If you have a domain — medicine, diplomacy, urban planning, education — and you're frustrated by polarised thinking, let's talk about building a skin together.

Get in touch
Join the Network

Be part of what comes next.

Whether you're a player, an organisation, or a potential collaborator — register your interest and we'll reach out when the time is right.