The mega-prompt that changed how I make decisions

There’s one prompt I run when I’m stuck on what to do next.

Not “what should I work on today” stuck. Bigger. The “I’m not sure my whole approach is still right” stuck.

It’s the closest thing I have to a brain reset.

Drop your context, run this prompt, and within a few minutes you have a list of options you wouldn’t have generated on your own — scored, filtered, and tied to one concrete action you can take in the next 24 hours.

I’ve used it to redesign my offer. Restructure my week. Rewrite my pitch. And once, to decide whether to keep building Waymaker at all.

It’s free. It works in any AI system that has decent context handling — Claude, ChatGPT, Gemini.

Step 1: Build a context document first (15 min)

The prompt is only as good as the context you feed it. Before running the prompt, spend 15 minutes writing a context doc with:

• Who I am — role, tenure, situation
• What I do — offers, customers, deliverables
• What I stand for — values, lines I won’t cross
• How I deliver value — process, what makes me different
• My current goal — what I’m trying to achieve in the next 90 days
• My timeline + budget — what I have to work with
• The tradeoff I’m willing to make — what I’d give up to get this
• 3 things I’m struggling with right now
• Things I’ve already tried that didn’t work, and why I think they failed

Be honest. Be specific. The model can only mentalist you to the depth you’re willing to write.

Step 2: Run the mega-prompt

Upload the context doc to Claude/ChatGPT/Gemini, then paste this:

“Here is who I am, what I do, what I stand for, and how I deliver value. I am ready and willing to burn down our current playbook and stand something new up in [TIMEFRAME] under [BUDGET] as long as it means [TRADEOFF GAINED] and a more sustainable path forward. Read what I have shared and build out a full profile of me. Build up my 5 layers of why. My 5 forces. My explicit and implicit values. My ghost or unnamed blockers. Things I haven’t mentioned and open questions you have. Be so thorough and cut so deep that it feels like a mentalist is peering inside my brain. Based on all the context I’ve provided, ideate several dozen potential workshift changes I can make from multiple angles (people, tech, environment, customers, combinations). Make them radically different. Then score them on likelihood to hit my timeline, budget, tradeoff gained. Then take the top 50%, and morph them — make edits that only experts in other fields would have brought up. Combine the evolved list with the original top 50%. Loop this process two more times. Present all top winning ideas back to me. Each idea should have a title, short description, and one concrete action I can take in the next 24 hours to kick it off. Be as specific and actionable as possible.”

Replace the bracketed parts with your actual numbers. Hit send. Make tea.

Step 3: Run three follow-up prompts

The first output is gold but it’s a list. Three follow-ups turn the list into a decision:

1. “Pick the top 3 ideas and explain what could go wrong with each.”
2. “If I can only do ONE of these in the next 30 days, which and why.”
3. “Convert the chosen one into a 7-day shipping plan.”

By the end of the third follow-up, you have a real plan. Not just a list of options.

Why it works

Most AI prompts ask the model to give you an answer. This one asks the model to give you options you wouldn’t have thought of, score them against your real constraints, then tell you what to do tomorrow.

The looping is what makes it different from a normal brainstorm. The first round generates options at your current ceiling. The morphing round adds expert lenses you don’t have. The third loop integrates them with your originals. By the end, you’re looking at moves that wouldn’t have come out of any single conversation — including one with yourself.

The 24-hour action is the safety net. It prevents this from becoming another planning loop. You don’t leave the prompt without doing one specific thing.

---

One thing to do today

If you’re stuck on something bigger than “what should I do today” — this is the move.

If you want a faster on-ramp, take the free 3-minute AI Skills Audit first. It’ll tell you which builder type you are, which gaps are biting you most, and which playbooks would compound fastest for someone in your situation. Then run the mega-prompt with that context already in hand.

Credit where it’s due: this prompt is adapted from work shared by Allie K Miller. I rewrote it for operator voice and built the context-doc structure to pair with it. The framework belongs to all of us — the only thing that matters is that you actually run it.