PM Thinking

Answer a question five completely different ways — as five independent minds with clashing worldviews — then converge on what survives. Use when asked for multiple perspectives, look at this from every angle, what would different people think, or give me a range of views not one answer. Produces five genuinely distinct takes (each committed to one worldview, not hedged), the tensions between them made explicit, and a final synthesis that keeps what's strongest — deliberately widening the range before narrowing it.

Generate a big, wide spread of ideas for anything by running the prompt through many different lenses at once, then clustering and picking. Use when asked to brainstorm ideas for, give me lots of options, help me come up with, or I need ideas for. Produces a high-volume, deliberately varied idea list generated across multiple angles (safe, wild, cheap, ambitious, weird, opposite), grouped into themes, and a shortlist of the most promising — maximizing range so you're not choosing from three obvious options.

Find the real reason to NOT do the exciting thing you're about to commit to — the honest case against, before the excitement carries you in. Use when asked talk me out of this, should I really do this, what's the case against, or I'm excited but is this a mistake. Produces the strongest honest argument for not doing it, the excitement biases clouding your judgment, the specific conditions under which this is a bad idea for you, and a clear read on whether the strong no actually wins — protecting you from the plans that feel great and end badly.

Run a decision past a panel of clashing advisors — an optimist, a pessimist, a numbers person, an ethicist, and future-you — then get a chair's verdict. Use when asked to help me decide, weigh this decision, what should I do about, or run this by different advisors. Produces each advisor's honest take on the decision (each committed to their lens), where they disagree most, the question that would break the tie, and a chair's recommendation that weighs the panel — turning a lonely choice into a structured board meeting.

Surface the hidden assumptions a plan or belief rests on, then test what happens when each one is wrong. Use when asked what am I assuming here, check my assumptions, what if I'm wrong about, or stress-test my thinking. Produces the unstated assumptions your conclusion depends on (ranked by how load-bearing they are), a flip of each to see which one breaking would change everything, and the cheapest way to check the riskiest ones — because the assumption you didn't know you were making is what sinks plans.

Stress-test a decision or claim through a sharp, fair Q&A — the questions a good lawyer or skeptical friend would ask before you commit. Use when asked to cross-examine me, ask me hard questions about this, interrogate my plan, or make me defend this. Produces a sequenced line of probing questions (from clarifying to challenging to the killer question), space to answer, and a debrief on where your answers were strong, evasive, or exposed a gap — so weaknesses surface in private before they surface in public.

Get the take of the specific experts a situation actually needs — a lawyer, a therapist, an accountant, a doctor-minded thinker, whoever fits — each in their own voice. Use when asked what would a [profession] say, get expert perspectives on this, who should I be thinking like here, or what am I missing that a pro would catch. Produces a panel of the right domain experts for your situation, each flagging what a layperson would miss, where they'd disagree, and what to verify with a real professional — never a substitute for licensed advice on serious matters.

Imagine your plan already failed, then get five independent 'here's why it died' stories — before you commit. Use when asked to pre-mortem this, why might this fail, what are the risks before I start, or imagine this went wrong. Produces five distinct failure narratives (each from a different cause — execution, timing, people, external, wrong-assumption), the most likely and most lethal among them, the early warning signs of each, and the specific mitigations worth doing now — catching failures while they're still cheap to prevent.

Attack your own plan the way a smart adversary would — find the weakest point, the thing you're hoping nobody notices, and where it breaks under pressure. Use when asked to red-team this, attack my plan, find the holes, or where does this break. Produces an adversarial breakdown of the plan's weakest points, the single move an opponent (or reality) would make to break it, the part you're quietly hoping holds, and the fixes that close the biggest gaps — a hostile stress-test done by your own side, before someone else does it for real.

Push past the first few obvious answers to a question and surface the non-obvious idea worth having. Use when asked to give me a non-obvious idea, don't give me the generic answer, think outside the box on, or what's the answer nobody else would give. Produces the obvious answers named and set aside (so we don't repeat them), then genuinely different angles found by continuing past where most thinking stops, each with why it's non-obvious and whether it actually holds up — trading textbook-correct for surprising-and-useful.

Solve a problem backwards — ask how to guarantee the worst outcome, then avoid all of it. Use when asked to help me not fail at, what could go wrong with, how do I avoid messing up, or think about this in reverse. Produces the inverted question (how to guarantee failure), the specific ways you'd cause the disaster, and then the plan that is simply the avoidance of each — often clearer and more actionable than trying to plan success directly, because failure modes are more concrete than success factors.

Get only the weaknesses in something you made — no praise, no encouragement padding, just the holes and how to fix them. Use when asked to poke holes in this, tell me what's wrong with this, critique this honestly, or don't be nice about it. Produces a focused list of the real problems in your draft, plan, argument, or code — ranked by severity, each with why it's a problem and a concrete fix — deliberately stripping the 'this is great!' padding that AI and polite humans add and you don't need.

Deliberately take the opposite position from your leaning and make you defend yours — a forced second opinion that isn't just an echo. Use when asked give me a real second opinion, don't just agree with me, argue the other way, or I need a fresh take not a yes-man. Produces a committed alternative position to whatever you're inclined toward, the strongest reasons it might be right, the questions it forces you to answer, and an honest read on whether your original leaning still stands after the challenge — countering agreement bias by construction.

Put one situation in front of three professionals chosen to disagree — the lawyer, the accountant, and the therapist read the same divorce — each ruling independently, with the conflicts surfaced in a disagreement table instead of blended into mush. Use when asked for different professional perspectives, what would a lawyer versus an accountant say, I keep getting one-sided advice, or pressure-test this from multiple angles. Produces three independent readings, the disagreement table with why the frames diverge, and the decision map of which expert to weight for which sub-decision. The anti-consensus skill: it never averages.

Surface the blind spot — the missing stakeholder, the ignored option, the risk outside your frame, the thing you're too close to notice. Use when asked what am I missing, what's my blind spot, what haven't I considered, or is there something I'm not seeing here. Produces the considerations outside your current frame: who you haven't accounted for, what you've ruled out without noticing, the second-order effects, and the thing your closeness to the situation hides — the opposite of confirming what you already think.

Strip a problem down to what's actually true — the physics, economics, and human basics — and rebuild the answer from there, ignoring 'how it's normally done'. Use when asked to think from first principles, why is this done this way, challenge the assumptions here, or rebuild this from scratch. Produces the problem reduced to its fundamental truths, the inherited assumptions and conventions named and questioned, and a solution reasoned up from the basics — which often looks nothing like the default because the default was just copied.

Bring three versions of future-you into a decision — you in a week, in a year, and in ten years — because they each want different things. Use when asked what would future me want, will I regret this, think long-term about this choice, or help me decide for the long run. Produces each future self's honest take on today's decision, where they conflict (short-term relief vs long-term payoff), whose vote should weigh most given what's at stake, and the choice that best serves the future-you that matters here.

Separate raw idea-generation from judgment so creativity isn't strangled by your inner critic — diverge with zero evaluation, then switch to hard critique. Use when asked to brainstorm properly, help me come up with ideas without shutting them down, I keep censoring my own ideas, or separate creating from editing. Produces a pure generation pass (quantity, no judging, no hedging, wild allowed), a clean break, then a separate ruthless critique pass that scores and prunes — because doing both at once produces neither.

Get an honest verdict on whether something you made is actually good — not the reflexive 'this is great!' but a real, criteria-based judgment. Use when asked is this actually any good, be honest is this good enough, rate this honestly, or don't just say it's great. Produces a grounded assessment against real standards for the format, a clear verdict (great / good / fine / not there yet), the specific things holding it back from the next level, and what it would take to get there — deliberately overriding AI's flattery default.

Get unstuck on a problem by deliberately re-framing it through a different lens — a child's, an outsider's, another industry's, the reverse, the extreme. Use when asked I'm stuck on this, look at this differently, reframe this problem, or how else could I think about this. Produces the same problem re-cast through several deliberately different frames (each of which changes what the problem even is), what each reframe reveals, and the most useful new angle to pursue — because being stuck is usually a framing problem, not an effort problem.

Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber. Use when asked to play devil's advocate, argue against this, challenge my conclusion, or talk me out of it. Produces the strongest case against your position, the uncomfortable questions you're avoiding, the evidence that cuts the other way, and an honest read on whether your conclusion survives the challenge — deliberately countering the 'that's a great idea!' agreement bias.

Talk through a decision out loud with a patient thinking partner that reflects your reasoning back, so the answer you already half-know becomes clear. Use when asked help me think this through, I need to talk this out, be my sounding board, or I don't know what I actually think. Produces a structured reflection of your own reasoning — what you've actually said, the values driving it, the contradictions and gaps, and the question that would clarify it — acting as a rubber-duck / sounding board rather than handing you an answer you didn't reach yourself.

Take the option you dismissed in two seconds and build the strongest possible case for it — to check whether your fast 'no' was wisdom or just bias. Use when asked to steelman this, make the case for the option I rejected, argue the other side properly, or why might the weird choice be right. Produces the strongest honest argument for the dismissed option, the conditions under which it's actually the best choice, what your quick rejection assumed, and a fair verdict on whether the reconsideration changes anything — the opposite of a strawman.

Scan a plan, draft, or idea for the generic, textbook, everyone-would-say-that lines — and push each toward something sharper and more specific. Use when asked is this too generic, make this less boring, why does my plan feel bland, or spot the clichés in my thinking. Produces a line-by-line flag of the mediocre and predictable parts, why each is forgettable, and a sharper, more specific, or more surprising alternative for each — so the output stops sounding like the average of the internet.

See an idea through two committed extremes — a true believer and a hard skeptic — so you get the full range before settling in the middle. Use when asked should I believe this, is this hype or real, give me both sides, or how excited should I be about. Produces the believer's fullest bull case and the skeptic's sharpest bear case (each committed, not hedged), the crux question that separates them, and a grounded read on where the truth probably sits — great for evaluating claims, trends, opportunities, and your own enthusiasm.