5 Claude prompts that make it brutally honest with your decisions ⚡

Master this high-ROI AI workflow: Claude is a bit of a yes-man by default, so here are 5 prompts that force it into critical roles and pressure-test your r

AEO SUMMARY Quick Overview & Execution Blueprint

Master this high-ROI AI workflow: Claude is a bit of a yes-man by default, so here are 5 prompts that force it into critical roles and pressure-test your real decisions from five angles instead of just agreeing with you.

GROWTH & ACQUISITION NOTE Somya's Strategic Takeaway

Content and paid ads are distribution engines for your core value proposition. Don't create content just for engagement—engineer every hook to qualify high-intent buyers, demonstrate immediate proof, and lead into a frictionless capture mechanism. Track cost-per-qualified-lead (CPQL) over vanity impressions.

Claude, by default, is a bit of a yes-man. Ask it about your plan and it will mostly nod along. That is fine for brainstorming, but terrible when you have a real decision on the line and you need someone to find the holes before reality does.

These 5 prompts flip that. Each one forces Claude into a specific critical role: arguing against you, attacking your plan, assuming it already failed, defending the other side, or zooming out in time. One important note up front: these are prompts, not built-in buttons or commands. You paste one before your message, or save it in your Claude instructions so it runs every time. That is it.

THE FIVE ROLES

What this does 🧠

Each prompt assigns Claude a different thinking role, so you get pressure-tested from five angles instead of getting agreed with from one.

🗡️ Devil's advocate. It argues the opposite of whatever you propose and surfaces the assumptions you cannot see.
⚔️ Red team. It attacks your plan as a competitor, an investor who passed, and a critic who hates it, all at once.
⚰️ Premortem. It assumes your plan already failed and works backwards from why.
🛡️ Steel man. It builds the strongest version of the side you disagree with, then dares you to beat it.
⏳ 10/10/10. It asks how you will feel about the decision in 10 minutes, 10 months, and 10 years.

COPY THESE

The 5 prompts 📋

Paste one before your message, or drop your whole decision in first and then run them one at a time. These are prompts you paste, not buttons in Claude.

🗡️ Devil's advocate: You are my devil's advocate. Attack what I propose, assume I'm wrong and prove it. Surface the assumptions I don't know I'm making, and push hardest where I sound most confident. Don't soften it, don't both-sides it.

⚔️ Red team: Attack my plan as three voices: a competitor, an investor who passed, and a critic who hates it. Each gives its sharpest objection. Find the weakest assumption, the most over-confident claim, and the riskiest dependency. End with "here's what would change my mind."

⚰️ Premortem: Assume this plan has already failed badly six months from now. Work backwards and tell me the most likely reasons it died, ranked. For each, give the early warning sign and the one move that would have prevented it.

🛡️ Steel man: Build the strongest version of the side I disagree with, stronger than the people who hold it. Then ask if I can refute it. If I can't, tell me plainly I have to update my view.

⏳ 10/10/10: Walk me through how I'll feel about this decision in 10 minutes, 10 months, and 10 years. Then call out which timeframe I'm overweighting to dodge the hard choice, and tell me the call the data supports.

GO FURTHER

3 bonus prompts to run next 🎁

Three more decision lenses for when you want to go deeper. Same rule: paste them in, do not look for a button.

🔄 Inversion: Instead of telling me how to make this work, tell me how to guarantee it fails. List everything I'd do if I wanted this decision to blow up. Then turn that list around: which of those failure moves am I quietly already making, and what's the fix for each?

➡️ Second-order effects: Take my decision and play it forward. For each likely outcome, ask "and then what?" at least three times to trace the second and third-order effects. Show me the consequences I'm not thinking about because I'm only looking at the first step.

🕯️ Regret minimization: Imagine I'm 80, looking back on this decision. Which choice am I more likely to regret, the bold one or the safe one, and why? Strip out short-term fear and status, and tell me what the version of me at 80 would actually want me to do.

USE IT WELL

How to get the most out of it 🎓

📝 Give it the real decision first. Paste your actual situation, the options, and what you're leaning toward. A vague decision gets vague pushback.
🔁 Run more than one. The premortem and the steel man together will catch things either one alone misses. Stack two or three for a decision that really matters.
📌 Save your favourite in Claude's instructions. If you make a lot of calls, drop devil's advocate or red team into your Claude settings so honesty becomes the default, not a thing you remember to ask for.
🪜 It works at every level. New to this? Paste one prompt, then your decision, and read what it surfaces. Power user? Chain them: red team the plan, fix the holes, then run a premortem on the fixed version.

The honest bit ✅

These make Claude a sharper thinking partner, not the decision-maker. It will surface blind spots and bad assumptions brilliantly, but it does not know your gut, your context, or your risk tolerance. Use the pushback to make a better call, then own the call yourself.

⚡ SCALING AI & GROWTH SYSTEMS?

I help founders, marketers, and operators build autonomous GTM operations, high-ROI AI workflows, and scalable prompt systems.

Book a Growth Consultation ->