9 Prompts for stuck problems

My default move on a hard problem was embarrassing

August 12, 2026

In partnership with

Something breaks, I open a search tab, I type the issue in, I scroll ten blue links, I skim a forum thread from 2019, and I end up making the same guess I would have made before opening the browser.

I have done that more times than I want to admit, which is why a post from an operator who recently sold his company stopped me mid scroll.

His point was blunt. Most people search their problems. A smaller group prompts their way through them. The difference between the two groups is not intelligence, it is tooling. One side searches and guesses. The other has a repeatable system for working through anything.

Blu Dot surpasses 2,000% ROAS with self-serve CTV ads

Home furniture brand Blu Dot blew up on CTV with help from Roku Ads Manager. Here’s how:

After a test campaign reached 211,000 households and achieved 1,010% ROAS, the brand went all in to promote its annual sales event. It removed age and income constraints to expand reach and shifted budget to custom audiences and retargeting, where intent was strongest.

The results speak for themselves. As Blu Dot increased their investment by 10x, ROAS jumped to 2,308% and more page-view conversions surpassed 50,000.

“For CTV campaigns, Roku has been a top performer,” said Claire Folkestad, Paid Media Strategist, Blu Dot. “Comping to our other platforms, we have seen really strong ROAS… and highly efficient CPMs, lower than any other CTV partner we've worked with.”

Using Roku Ads Manager, the campaign moved from a pilot to a permanent performance engine for the brand.

*Ad

The line that reframed it for me

Winning teams are not the ones with the most resources. They are the ones with the tightest feedback loop between thinking and deciding.

He said that when he sold his last company, the thing separating them from competitors was not the product. It was how quickly they could diagnose what was not working, decide what to do next, and move. Speed of judgment, not headcount.

That skill used to live in expensive rooms with expensive people. Now it fits inside a chat window and a handful of well-shaped questions.

He covered twenty prompts in total. These are the nine he reaches for most when he is stuck, each one a different angle on the same goal: think clearly, then decide fast.

The nine prompts worth stealing

  1. Root Cause Analyzer. Quit treating symptoms. This one forces you to find what is actually broken before you take a single action. Most bad decisions come from fixing the wrong thing, and this kills that habit quickly.

  2. Decision Matrix Builder. It scores every option across time, cost, risk, and upside. No more gut-feel calls that quietly waste months. You see the tradeoffs laid out in one clean grid.

  3. First Principles Breakdown. Strip the problem down to its raw components, then rebuild it from scratch with fresh eyes. It is the antidote to we have always done it this way.

  4. Constraint Removal. It maps every limit holding you back, then sorts them into two piles: the real ones and the ones you invented in your own head. You will be surprised how many are imaginary.

  5. Tradeoff Analysis. Shows you exactly what you gain and lose on each path. He calls it a cure for false clarity, that feeling of certainty that is not backed by anything real.

  6. Failure Prevention. Run a pre-mortem before you launch. You assume the project already failed, then work backwards to figure out why. It surfaces risks you would never spot looking forward.

  7. Reverse Engineering. Start from the outcome you want and map every dependency backwards to today. Instead of guessing your first step, you build the whole chain in reverse.

  8. Strategic Risk Mapping. This covers the scenarios most founders skip: legal, financial, execution, and market. The uncomfortable stuff that sinks companies quietly.

  9. Complete Problem Solving Framework. One master prompt that runs the full sequence, from diagnosis all the way to an action plan. Think of it as the previous eight stitched into a single flow.

The GTM Playbook Behind Warmly's Acquisition

Warmly ran pipeline, outreach, and lead scoring on autopilot for hundreds of startups — before a single sales hire.

HubSpot acquired them for it. Now the cofounders are walking you through the exact system, live, before they disappear into product. Join the Builder Session on August 12.

Leave with an agentic GTM stack you can replicate this week. Plus HubSpot Credits when you join HubSpot for Startups.

*Ad

How to actually use them

Reading a list like this is the easy part. Building the habit is where it falls apart, so here is the smallest possible version.

Pick one problem you are stuck on right now. Not a hypothetical, not a nice example. The real one sitting on your desk today.

Start with Root Cause Analyzer, before you brainstorm a single solution, because making sure you are solving the right problem saves more hours than any other step in the sequence.

Move to Decision Matrix Builder once you have options on the table. Let the scoring expose your bias rather than giving you a place to defend it.

Then run Failure Prevention before you commit to anything. A five minute pre-mortem beats a five week cleanup, every time.

Notice the loop hiding in those four steps. Diagnose, decide, stress-test, move. That is the feedback loop he says separates winning teams from merely busy ones. The prompts are just the rails that keep you on it.

The gap forming inside every company

There is a quiet split happening in most organizations right now, and almost nobody has named it out loud yet.

On one side are the people who search, scroll, and guess their way through hard problems. On the other are the people running a repeatable system. The second group is not smarter. They simply have better tools for thinking.

The encouraging part is that the system is not gated behind a degree or a budget. It is a handful of prompts and the discipline to actually use them when you are tired and would rather just decide.

See how AI delivers fast, secure, personalized experiences

Join Fin and Plaid on August 13th to see how AI can resolve issues directly in customer conversations. This includes everything from reducing bank-linking friction, enabling proactive support, and helping customers complete real financial tasks.

*Ad

None of these are clever tricks

That is what I appreciate about the list. They are structured thinking tools wearing prompt costumes. You could run any one of them on a whiteboard with a marker and get most of the value.

ChatGPT just makes the process faster, and more importantly, it keeps you honest at the exact moment you would rather skip a step. The pre-mortem is the one everybody skips. The prompt does not let you.

The problem on my desk tonight

What got me about this list was not any single prompt. It was realizing how often I skip straight to solutions because diagnosis feels slow, and then spend a week undoing work that was aimed at the wrong target.

The sequence fixes that by making the boring step unavoidable. Diagnosis first, always, even when you are certain you already know the answer. Especially then.

So try this tonight. Take the one decision you have been circling for a week, open a fresh chat, and run the root cause question on it before you look at any options. Then run a five minute pre-mortem on whatever you were about to choose. If both agree with your instinct, move with confidence. If they do not, you just bought back a week you were going to lose anyway.