Skip to main content
MethodBusiness Strategy & PlanningStrategy & planningAdvanced

Plan for uncertainty with scenarios

Four plausible future scenarios built from two critical uncertainties, with signposts and no-regret moves.

This is a practical, copy-paste process for the future depends on things you cannot control (rates, regulation, technology).. Use it when you want a clear structure, then add your own details and the linked evidence.

Published by Deepstory Research. Reviewed Sep 2026.

How to use this method

  1. 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
  2. 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
  3. 3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.

The prompt

Paste it as-is. The AI will ask for anything still in [BRACKETS].

Download .md
# 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.

What you need to give the AI

InputPlaceholderExample
Decision or organisation[DECISION_OR_ORGANISATION]building a new cold-storage warehouse
Horizon[HORIZON]2030
Key uncertainties you already see[KEY_UNCERTAINTIES_YOU_ALREADY_SEE]fuel prices, e-grocery adoption

Use it when

  • The future depends on things you cannot control (rates, regulation, technology).
  • Stress-testing a long-term plan.

What you get

  • Driving forces
  • 2×2 scenario matrix
  • Scenario narratives
  • Implications per scenario
  • Signposts to monitor
  • No-regret moves

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

  1. 1

    List driving forces; separate predetermined trends from critical uncertainties.

  2. 2

    Pick the two most impactful, most uncertain drivers as axes.

  3. 3

    Write four named scenarios with a short narrative each.

  4. 4

    For each scenario: what the plan must do, and signposts that it is unfolding.

  5. 5

    Identify no-regret moves that work in all four.

Quality checks built into the prompt

  • • Scenarios must be plausible, not best/worst cases.
  • • Signposts must be observable data, not opinions.
  • • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence to use with this method

Methods tell the AI how to think. Evidence gives it sourced numbers to think with. Download a context file and attach it with the prompt.

EvidenceEnergy

US Oil & Gas Dashboard

Every key US oil & gas number on one page: the 2026 crude-price shock from the Strait of Hormuz, Henry Hub natural gas, record US crude production, a depleted Strategic Petroleum Reserve, the drilling rig count, and what it all means at the pump.

Open evidenceDownload context file

Run next

Methods that chain well after this one.

Business Strategy & PlanningCompare strategic options in a decision memoA crisp memo comparing 2–4 options against explicit criteria, ending in one recommendation.Legal, Risk & ComplianceBuild an enterprise risk registerA company-level risk register with categories, scores, owners, controls and appetite.Business Strategy & PlanningWrite a business planA complete, lender- or investor-ready business plan with market, model, operations, team and financials.Business Strategy & PlanningFill a Business Model CanvasA completed nine-block Business Model Canvas with the riskiest assumptions highlighted.

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