---
type: method
slug: scenario-planning
title: "Plan for uncertainty with scenarios"
category: "Business Strategy & Planning"
subcategory: "Strategy & planning"
level: advanced
source: https://deepstoryresearch.com/method/scenario-planning
publisher: Deepstory Research
---

> **How to use this file:** attach it to ChatGPT, Claude, Gemini or Copilot (or paste the prompt section), replace every [PLACEHOLDER] with your details, and add any data or Deepstory evidence files the method needs.

## When to use this method
- The future depends on things you cannot control (rates, regulation, technology).
- Stress-testing a long-term plan.

## Prompt

# Plan for uncertainty with scenarios
Method by Deepstory Research: deepstoryresearch.com/method/scenario-planning

You are a scenario planner in the Shell tradition. Follow the method below step by step. Goal: Four plausible future scenarios built from two critical uncertainties, with signposts and no-regret moves.

## My inputs
- Decision or organisation: [DECISION_OR_ORGANISATION]  (example: building a new cold-storage warehouse)
- Horizon: [HORIZON]  (example: 2030)
- Key uncertainties you already see: [KEY_UNCERTAINTIES_YOU_ALREADY_SEE]  (example: fuel prices, e-grocery adoption)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. List driving forces; separate predetermined trends from critical uncertainties.
2. Pick the two most impactful, most uncertain drivers as axes.
3. Write four named scenarios with a short narrative each.
4. For each scenario: what the plan must do, and signposts that it is unfolding.
5. Identify no-regret moves that work in all four.

## Deliver the output in this structure
- Driving forces
- 2×2 scenario matrix
- Scenario narratives
- Implications per scenario
- Signposts to monitor
- No-regret moves

## Quality rules
- Scenarios must be plausible, not best/worst cases.
- Signposts must be observable data, not opinions.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

## Evidence you can attach
- Six-Economy Macro Baseline: https://deepstoryresearch.com/data/global-macro-baseline (AI context file: https://deepstoryresearch.com/context/global-macro-baseline.md)
- US Oil & Gas Dashboard: https://deepstoryresearch.com/data/us-oil-gas (AI context file: https://deepstoryresearch.com/context/us-oil-gas.md)
- Shipping Chokepoints: https://deepstoryresearch.com/data/shipping-chokepoints (AI context file: https://deepstoryresearch.com/context/shipping-chokepoints.md)
- E-Commerce Share of US Retail: https://deepstoryresearch.com/data/us-ecommerce-share (AI context file: https://deepstoryresearch.com/context/us-ecommerce-share.md)

---
Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment matters need a qualified professional.