Best PromptsFour Futures Scenario Planning
Run the Shell scenario method on your own future: two critical uncertainties, four named futures, early-warning signposts, and moves that work in all four.
Run me through real scenario planning, the method Shell used to rehearse the 1973 oil shock before it happened, applied to a future I actually have a stake in.
My focal question: [THE DECISION OR DOMAIN, e.g. "what happens to my career as a designer over the next 5 years" / "whether to start a company in X" / "my industry through 2032"]
My time horizon: [YEARS]
Context about me: [YOUR SITUATION IN 2-4 LINES: role, industry, constraints, what you're weighing]
Work through the method with me, step by step, asking for my input at each step rather than generating it all yourself:
1. DRIVING FORCES. Together, list the forces that will shape this: social, technological, economic, environmental, political. Push me past the obvious ones; ask what forces I'm not naming because they're uncomfortable.
2. THE TWO AXES. Sort the forces by importance and by uncertainty. Things that are important but predictable (demographics, announced regulation) go into every scenario as givens. The two most important AND most uncertain forces become our axes. Propose your top candidates for the axes, with reasoning, and let me pick or override.
3. FOUR FUTURES. The two axes make a 2x2: four internally consistent worlds. For each: a memorable name, a one-paragraph story of how we got there from today (events in sequence, with rough years), what daily life looks like for someone in my position, who wins and who loses. Make each world genuinely plausible; no strawman utopias or doom cartoons. The test of a good scenario set: I should be unable to dismiss any quadrant.
4. THE STRESS TEST. Take the decision or plan I care about into each world. Where does it thrive, survive, die? Which world am I implicitly betting on right now without admitting it?
5. ROBUST MOVES AND REAL OPTIONS. Identify: moves that pay off in all four worlds (do these regardless), cheap options that hedge the worst world, and the one bet that only makes sense if I'm confident which world is coming, flagged as the risk it is.
6. SIGNPOSTS. For each world, three early-warning indicators: observable, dated, specific ("X ships a production version by mid-2027", not "AI keeps improving"). These tell me which future is arriving while there's still time to act.
7. THE FORECAST CARD. End with five falsifiable predictions relevant to my question, each with a probability and a resolution date, plus my own probability estimate for which quadrant we land in. I'll score these when the dates arrive: calibration beats vibes.
Rules: futures thinking fails by extrapolating straight lines, so watch for S-curves (every exponential is an S-curve early on) and remember short-run change gets overestimated while long-run change gets underestimated. Where the honest answer is "nobody knows", say it, and put it on an axis instead of pretending.How to use
This is the Global Business Network method (Peter Schwartz, The Art of the Long View) with Tetlock-style scored forecasting bolted on, personalized instead of corporate. The step that changes minds is 4: most people discover they've been silently betting everything on one quadrant. Put the signposts and forecast card somewhere you'll see them; rerun the exercise when a signpost fires. One session covers one focal question; resist cramming in two.
More rabbit hole prompts
Take me down into gratitude, past the list. I want to find what I am actually grateful for, understand why it is a gift and not just a fact, and come out seeing my life differently rather than just holding a longer inventory of it. A list is where most gratitude stops. It is where this starts. Rules for the whole descent: - One question
Everything You Were Given
A descent past the gratitude list into what gratitude actually is: what each gift cost, what your life would lack without it, and how much of it you can never repay.
Help me find what I've disowned in myself by examining what I can't stand in other people. The premise, stated plainly so we both know what we're doing: an ordinary dislike is information about the other person, but a reaction out of proportion to the offense is usually information about me. Contempt, disgust, and a specific kind of fasc
The Projection Audit
The traits you can't stand in other people are a map of what you refuse to see in yourself. This walks the map, using your own irritations as data.
Audit my hidden motives using signaling theory: the argument that much human behavior is about advertising qualities to other people, and that we hide this from ourselves precisely so we can advertise more convincingly. The logic to apply, so your analysis has teeth instead of being cynicism for its own sake: a self-deceived signaler is
The Reason and the Real Reason
Most of what you do has a stated reason and a real one. Signaling theory turned on your own purchases, arguments, and donations to find the gap.