Blog
Top 12 Viral Prompts for Productivity - #123
ai agentic systems agentic models ai help ai prompts ai tips

Top 12 Viral Prompts for Productivity - #123

Unlock your brain for ai to use

April 10, 2026 2 min read 482 words 40 reactions Read on Substack →

I know 3 languages (functional), 4 if you count my terrible Hindi I picked up while in India. What I have found is that learning to leverage ai prompting well, one must actually ‘learn a new language.’ In my client coaching, I spend a good amount of time on prompting semantics and context, however, there are even better ways of leveraging your agent to extract more information out of you.

Here are 12 amazing prompts I’ve sourced and used to help improve your use of ai when building anything.

1. The “Contradictions Finder” - Perfect for papers, reports, or long docs.

“List all internal contradictions, unresolved tensions, or claims that don’t fully follow from the evidence.”

It catches things humans gloss over.

2. The “Reviewer #2” prompt - Yes, that reviewer.

“Critique this like a skeptical peer reviewer. Be harsh. Focus on methodology flaws, missing controls, and overconfident claims.”

Brutal. Necessary.

3. The “Turn This Into a Paper” prompt - Use this when you dump raw notes, links, or half-baked ideas.

“Turn the following material into a structured research brief. Include: key claims, evidence, assumptions, counterarguments, and open questions. Flag anything weak or missing.”

This alone replaces hours of cleanup.

4. The “Explain It Backwards” trick - Great for checking real understanding.

“Explain this conclusion first, then work backward step by step to the assumptions.”

If the logic collapses, you’ll see it immediately.

5. The “Compare Like a Scientist” prompt - Not feature lists. Real comparisons.

“Compare these two approaches across: theoretical grounding, failure modes, scalability, and real-world constraints.”

6. The “What Would Break This?” prompt - Gold for forecasting.

“Describe scenarios where this approach fails catastrophically. Not edge cases. Realistic failure modes.”


Most people never ask this.

7. The “What Changed My Mind?” closer - Get more feedback.

“After analyzing all of this, what should change my current belief?”

This is how real researchers think.

8. The “One-Page Mental Model” - Simple understanding.

“Compress this entire topic into a single mental model I can remember.”

If it can’t compress, you don’t own it yet.

9. The “Translate Across Domains” prompt - Understand potentials.

“Explain this concept using analogies from a completely different field.”

This unlocks insight, not just understanding.

10. The “Steal the Structure” trick - This is underrated.

“Ignore the content. Analyze the structure, flow, and argument pattern. Why does this work so well?”

Use it on great papers and essays.

11. The “Compare Like a Scientist” prompt - Not feature lists. Real comparisons.

“Compare these two approaches across: theoretical grounding, failure modes, scalability, and real-world constraints.”

12. The “Assumption Stress Test” - This one comes straight from research forums.

“List every assumption this argument relies on. Now tell me which ones are most fragile and why.”

The world is filled with assumptions. Use ai to do the heavy lifting.

Any prompts you find amazing to use? Let me know!

Learn more ai for free here.

Best,
ps

About the Author

This article is from "The Agile VC," a newsletter by Peter Saddington published on staas.fund. Peter is a serial entrepreneur, venture capitalist (StaaS Fund, RegD 506B), and AI practitioner who has trained 17,000+ professionals in agile and AI methodologies. He bought Bitcoin at $2.52 in 2011, built 4 autonomous AI agents (the Council of Dogelord), and operates 10+ websites with zero employees. His AI Workshop has been attended by Fortune 500 teams. Peter holds 3 Master's degrees (Divinity, Computer Science, Computational Operations Research) from institutions including Georgia Tech. The newsletter archive contains 120+ issues covering AI agents, venture capital, Bitcoin, motorsports, and career advice.

Questions about this topic?

Ask Peter's AI — trained on this newsletter and 4 years of AI work.

Talk to Peter's AI →