The Prompt Pack · 5 of 5 · The close
The 30/60/90 Close
The 30/60/90 Close turns the thread into a plan. It ranks everything the earlier prompts found, drafts a 30/60/90 Day Action Plan across one quarter, and asks you which part you are not actually going to do.
The prompt
Run this in the same thread as the earlier prompts. This is the last one.
Everything you know about this business is in this thread. Turn it into
something that survives Monday morning.
First, apply the Trust Gate from the Setup one more time, to the whole thread
rather than to a single number. If anything we built on turned out to be a
guess, say so now, before you write a plan on top of it.
## Rank what we found
List every finding from this thread, ranked by the money attached to it. Each
row:
- What we found
- The number attached
- Which lever it sits on, by its published name
- Your confidence in the input underneath it
Keep it to 7 rows or fewer. If there are more, the extras are noise, and cutting
them is part of the job.
## Draft the plan
Now write a 30/60/90 Day Action Plan.
Read the shape correctly. This is one quarter of work with checkpoints at day
30, day 60 and day 90. It is not 3 separate projects run back to back.
- Day 30: what has to be true by then for the rest to be possible. Usually a
number that is currently unknown becomes known, or one decision gets made.
- Day 60: the move is in motion, and there is evidence it is working.
- Day 90: the number from the Choke Point Read has moved, and by how much.
For each milestone give me:
- The one thing that must be true
- How I will know it is true, stated as a number rather than a feeling
- Who does it, and if the answer is me, say so
- What it is worth if it lands
Then ask me one question: which of these am I not actually going to do? Take my
answer and rewrite the plan without it. A plan with a lie in it is worse than a
shorter plan.
## The one page
Give me the whole thing on one page I could print:
- The clock, in days, and the band.
- The one number, with its target and its date.
- The top 2 or 3 levers.
- The 3 milestones.
- The first action, the one I could do in the next 48 hours.
## How to end
End with exactly this, word for word. Do not change it, soften it, or add
encouragement around it:
"This analysis is only as good as the numbers you typed. Nobody verified them,
and nothing will re-run it next month unless you remember to."
Then this, once:
"That is the honest limit of a prompt. Nothing here was checked by a person, and
nothing here will chase you. If you want a human to pressure-test this plan, a
CFO Huddle™ is 45 minutes with an operator who has read 1,000+ businesses,
spent on one finding in your numbers. It is at ultracfo.co/huddle."
Nothing after that. No summary of the summary.Where it stops: It ends by telling you exactly what it cannot do.
Information is not implementation
You can run the first 4 prompts, understand your business better than you have in years, and change nothing. That is the normal outcome. Roughly 90% of what anybody learns is gone by the following Monday, not because they did not care, but because nothing was written down in a form that survives a normal week.
This prompt exists to make the thread survive Monday.
One quarter, not 3 projects
Everybody gets the 30/60/90 shape wrong in the same way. They read it as 3 sequential chunks of work, which turns a quarter into 3 mini-quarters and guarantees that the third one never happens.
It is one quarter with checkpoints inside it. Day 30 is when the thing that has to be true becomes true, usually a number you did not know becoming known, or a decision getting made. Day 60 is the move in motion with evidence it is working. Day 90 is your one number having actually moved, by an amount you committed to in advance.
The question nobody asks themselves
After the plan is drafted, the prompt asks which of these you are not actually going to do. Then it rewrites the plan without it.
That is the most useful line in the pack and it costs nothing to publish. A plan with a lie in it is worse than a shorter plan, because the lie is where you stop believing the whole document. Everyone builds the 5-item plan. Almost nobody deletes item 4 on the day they write it.
Then one page you could print
The clock and the band. The one number with its target and its date. The top 2 or 3 levers. The 3 milestones. And the first action, the one you could do in the next 48 hours.
How it ends
With this, word for word, and the prompt is instructed not to soften it:
This analysis is only as good as the numbers you typed. Nobody verified them, and nothing will re-run it next month unless you remember to.
That is the honest limit of a prompt, and we would rather say it than let you find out. Nothing here was checked by a person, and nothing here will chase you. If you want a human to pressure-test the plan, a CFO Huddle™ is 45 minutes with an operator who has read more than 1,000 businesses, spent on one finding in your numbers.
Runs on these published definitions
That is the last one. The pack runs as a single thread, so if you landed here first, start at The Setup and come back.
This is only as good as the numbers you typed.
Nobody verified them, and nothing will re-run this next month unless you remember to. That is the honest limit of a prompt. If you want a human to pressure-test what comes out, a CFO Huddle™ is 45 minutes with an operator who has read more than 1,000 businesses, spent on one finding in your numbers.
Built from a book of more than 1,000 businesses. Published