LinkedIn Meeting Prep Prompt
A one-page brief you can read in the two minutes before a call, ending in the three questions that decide whether it goes anywhere. The last step of the outbound workflow and the one that is always rushed. It assembles what the thread already told you, marks what you are assuming, and produces the questions worth asking — including the disqualifying one most people avoid.
You are preparing a seller for a first call. The brief must be readable in under two minutes.
## Me
{{ROLE}} at {{COMPANY}} — {{PRODUCT}}
Proof I may cite: {{PROOF}}
What I want from the call: {{OBJECTIVE}}
## Them
{{PROSPECT_NAME}}, {{PROSPECT_ROLE}} at {{PROSPECT_COMPANY}}
Profile: {{PROSPECT_PROFILE}}
## The thread so far
[PASTE THE FULL THREAD WITH DATES]
## Method
1. Extract everything they have actually told me, quoted. Separate it from everything I have inferred.
2. Identify what I still do not know that would change how I run the call.
3. Write three questions. The first opens, the second tests the hypothesis, the third is the disqualifier — the question whose answer might end the deal and should therefore be asked early rather than late.
4. Name the two most likely reasons this does not close, and what I would look for in the call to confirm either.
5. Prepare one proof point matched to what they said, and note explicitly if my available proof does not match their situation.
## Constraints
- Quotes must be verbatim from the thread. Do not paraphrase into quotation marks.
- No discovery-question templates. Every question must be traceable to something in the material.
- Under 400 words total.
## Output format
### They told me
Quoted, with dates.
### I am assuming
Bullet list, honest.
### Three questions
Open / test / disqualify, one line each.
### Two ways this dies
And the early signal for each.
### Proof to have ready
Which one, and why it matches. Or: "nothing in my proof matches their situation" — say that if it is true.
### The one sentence to open with- You have a call in ten minutes and the thread is four weeks long.
- You are handing a meeting to an AE and need the context written down.
- You want your discovery questions to come from evidence rather than from a template.
- Paste the whole thread. The quoted section is the most useful part of the brief and it can only come from real text.
- Ask the disqualifying question in the first ten minutes. Saving it for the end is how a pipeline fills with deals that were never real.
- Keep the brief after the call and note which of the "two ways this dies" was right. That list becomes OBJECTIONS.md.
The output schema it demands
The single highest-leverage part of any prompt. Without a declared shape you get prose you then have to reformat; with one, you get sections you can act on — and you can tell at a glance when the model skipped something.
### They told me (quoted, dated) ### I am assuming ### Three questions (open / test / disqualify) ### Two ways this dies ### Proof to have ready ### The one sentence to open with
What it looks like filled in
Illustrative, not a promise — this is the shape of a good answer rather than a guarantee of one. The scenario is the same fictional company used across the whole toolkit.
Thread with Dana over three weeks: she confirmed the close is "annoyingly long" and agreed to a call Thursday.
They told me — "annoyingly long" (week 2), "since the acquisition" (week 1). Both quoted, not paraphrased.
Three questions — Open: "Walk me through what actually happens in week 3 of the close." Disqualify: "Is this budgeted for this year, or is it a someday problem?"
Two ways this dies — 1) It turns out to be a people problem rather than a process one — she just needs a hire. 2) No budget until next fiscal year.
The one sentence to open with — "Before we get into it — is week 3 the actual bottleneck, or does it just feel that way?"
Attach these once and stop retyping your business
This prompt works pasted into a blank chat. It works considerably better inside a Project with these attached, because then the ICP, the product and the limits are already in context and every answer inherits them.
This is one step in a sequence
The output of the step before is the input to this one, and this one's output is the next one's input. That is the whole reason these are not independent pages.
The reference behind this prompt
If the call turns into "which LinkedIn plan should we be on", this is the page to send afterwards.
Written to a fixed structure and run through Claude and ChatGPT to confirm each one returns the output format it declares. That is not the same as a measured reply-rate benchmark, and nothing here claims one — if you run these at volume and have numbers, we want them.
Take the whole folder instead
This prompt, the files it expects and the rest of the sequence, as a zip you can drop into a Claude Project, a Cursor workspace or an agent repo. Free, no account.