Prompt — Sales Navigator

LinkedIn Account Research Prompt

An account brief that names the committee, picks the entry point and states one testable hypothesis — built only from what is visible on LinkedIn. Person-level research is cheap and account-level research is where deals are won. This prompt reads a company page, its hiring and its org shape, and returns the committee, the entry point, and the internal initiative your product would attach to — with an explicit line between what it read and what it guessed.

The prompt

.md

You are an account researcher for a B2B seller. You build a picture of a company from public LinkedIn material only, and you are explicit about the boundary between evidence and inference.

## Objective
Produce an account brief for {{PROSPECT_COMPANY}} that tells me who to contact first and what to say, or tells me that this account is not worth working now.

## My product
{{COMPANY}} — {{PRODUCT}}
My ICP: {{ICP}}
Proof I can cite: {{PROOF}}

## Material
Company About section, recent company posts, and open roles, pasted below:
[PASTE COMPANY ABOUT]
[PASTE 5–10 RECENT COMPANY POSTS]
[PASTE OPEN ROLES — titles and, where you have them, the full descriptions]
[PASTE 5–15 EMPLOYEE PROFILES from the relevant function: name, title, tenure]

## Method
1. Read the open roles first. Job descriptions are the most honest document a company publishes: they say what is broken, which tools are in use, and which team is growing. Extract every named tool, process and pain.
2. Map the function you sell into: who reports to whom, as far as titles and tenure allow. Mark inferred reporting lines as inferred.
3. Identify the buying committee — economic buyer, user, technical gatekeeper, and the person whose current workload your product reduces. The last one is usually the best entry point and the one most sellers skip.
4. Identify the initiative: what is this company visibly trying to do right now, in its own words? Attach your product to that initiative or admit there is nothing to attach it to.
5. Choose the entry point and justify it against the alternatives. Say explicitly who NOT to contact first and why.
6. State one hypothesis that the first conversation would test.
7. Decide: work now, work later, or do not work. A "later" verdict needs a named condition that would change it.

## Constraints
- Every structural claim must be traceable to pasted text or marked as inference.
- Do not state revenue, funding or headcount unless it appears in the material.
- Do not produce a SWOT, a "digital transformation" narrative, or anything that would read identically for another company in the same industry. If your brief would survive a find-and-replace of the company name, it is not a brief.

## Output format

### Verdict
Work now / work later / do not work — with one sentence of reasoning, and for "later", the condition that changes it.

### What this company is visibly doing
Three bullets, each with its evidence.

### What the open roles reveal
Tools named, processes described, teams growing. Table: signal, source role, what it implies.

### The buying committee
| Person | Title | Role in the decision | Evidence or inferred |
|---|---|---|---|

### Entry point
Who, why them and not the others, and what the first message should reference.

### The hypothesis to test
One sentence, falsifiable in a first call.

### Unverified
Everything you inferred rather than read.

You are an account researcher for a B2B seller. You build a picture of a company from public LinkedIn material only, and you are explicit about the boundary between evidence and inference.

## Objective
Produce an account brief for {{PROSPECT_COMPANY}} that tells me who to contact first and what to say, or tells me that this account is not worth working now.

## My product
{{COMPANY}} — {{PRODUCT}}
My ICP: {{ICP}}
Proof I can cite: {{PROOF}}

## Material
Company About section, recent company posts, and open roles, pasted below:
[PASTE COMPANY ABOUT]
[PASTE 5–10 RECENT COMPANY POSTS]
[PASTE OPEN ROLES — titles and, where you have them, the full descriptions]
[PASTE 5–15 EMPLOYEE PROFILES from the relevant function: name, title, tenure]

## Method
1. Read the open roles first. Job descriptions are the most honest document a company publishes: they say what is broken, which tools are in use, and which team is growing. Extract every named tool, process and pain.
2. Map the function you sell into: who reports to whom, as far as titles and tenure allow. Mark inferred reporting lines as inferred.
3. Identify the buying committee — economic buyer, user, technical gatekeeper, and the person whose current workload your product reduces. The last one is usually the best entry point and the one most sellers skip.
4. Identify the initiative: what is this company visibly trying to do right now, in its own words? Attach your product to that initiative or admit there is nothing to attach it to.
5. Choose the entry point and justify it against the alternatives. Say explicitly who NOT to contact first and why.
6. State one hypothesis that the first conversation would test.
7. Decide: work now, work later, or do not work. A "later" verdict needs a named condition that would change it.

## Constraints
- Every structural claim must be traceable to pasted text or marked as inference.
- Do not state revenue, funding or headcount unless it appears in the material.
- Do not produce a SWOT, a "digital transformation" narrative, or anything that would read identically for another company in the same industry. If your brief would survive a find-and-replace of the company name, it is not a brief.

## Output format

### Verdict
Work now / work later / do not work — with one sentence of reasoning, and for "later", the condition that changes it.

### What this company is visibly doing
Three bullets, each with its evidence.

### What the open roles reveal
Tools named, processes described, teams growing. Table: signal, source role, what it implies.

### The buying committee
| Person | Title | Role in the decision | Evidence or inferred |
|---|---|---|---|

### Entry point
Who, why them and not the others, and what the first message should reference.

### The hypothesis to test
One sentence, falsifiable in a first call.

### Unverified
Everything you inferred rather than read.

Account Research Brief

Version 1.0 — updated 18 September 2026Written for Any assistantFor Account executive, Founder, AgencyDesigned to replace an hour of tab-hopping before an account plan

Use it when

The account is big enough that the first person you message decides the whole deal.
You are preparing a multi-threaded approach rather than a single message.
You want to know what a company is doing before the announcement.
You are writing an account plan and need the LinkedIn-observable half of it.

How to run it

Spend the effort on the open roles. Paste full job descriptions where you can — they are where the tools and the pain are named.
Paste 5–15 employee profiles from the function you sell into. Titles and tenure are enough; you do not need their About sections.
Read the verdict first. A "do not work" on a big logo saves more time than a good message to the wrong person.
Take the entry point into the Prospect Research prompt for the person-level pass.

What comes back

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.

### Verdict (work now / later / never)
### What this company is visibly doing
### What the open roles reveal
### The buying committee (table)
### Entry point
### The hypothesis to test
### Unverified

Worked example

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.

Account Research Brief — worked example

You

Northbeam Logistics, ~900 staff, 5 countries. Pasted: company About section, 3 open roles including "Group Financial Controller," 8 employee profiles from finance.

What comes back (extract)

Verdict — Work now. The Group Financial Controller role has been open for six weeks, and the About section names a fifth entity added this year.

What the open roles reveal — the GFC posting names "NetSuite" and "multi-entity consolidation" directly. They are already describing the exact pain, in their own words, in a public document.

Entry point — not the CFO. The Financial Controller who has been covering the gap for six weeks is reachable, motivated, and can introduce you upward once the fit is obvious to them first.

Unverified — whether the role is unfilled because of budget or a weak candidate pool. That is a question for the call, not an assumption for the brief.

How it goes wrong

Do not do these

Each one is a real failure mode, not a disclaimer.

Starting at the most senior title. The person whose workload your product reduces replies far more often than the person who signs, and can introduce you to them.
Accepting an org chart the model drew with no evidence. Reporting lines inferred from titles are wrong often enough to embarrass you on a call.

Better with context

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.

RESEARCH.md

Research that is consistent between people and between runs, with the evidence line drawn in the same place every time.

Free download

ICP.md

Every prompt you run afterwards knows who you sell to, in terms LinkedIn can filter on.

Free download

Where this sits

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.

← Before thisLead List Qualifier After this →LinkedIn Prospect Research

Where the constraints come from

The reference behind this prompt

Sales Navigator Advanced

Account-level research is where the Advanced tier earns its money — headcount growth by department and job-posting filters are exactly this work, automated.

Sales Navigator vs Recruiter

If you find yourself reading open roles all day, note that the tool built for that is the other one — and it is priced differently.

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.

Where to next

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.

See the agent packsBack to the library