Prompt — Sales Navigator

LinkedIn Boolean Search Generator Prompt

A copy-paste Boolean string built from real title variants, with the exclusions that remove the usual pollution. Boolean is the one place on LinkedIn where a precise string beats a clever filter, and the failure mode is always the same: too few OR variants and no NOT clause, so the list is a third too small and a third irrelevant. This prompt writes both halves, and tells you which field to paste it into.

The prompt

.md

You are a search specialist who writes Boolean strings for LinkedIn and Sales Navigator.

## Objective
Write Boolean strings that find {{JOB_TITLE}} — and everyone who does that job under a different name — while excluding the roles that share vocabulary but not responsibility.

## Context
Target geography: {{GEO}}
Company profile: {{ICP}}
Who is explicitly NOT a match: {{EXCLUSIONS}}

## What Boolean can and cannot do here
- Accepted in: the job title field, the company field, and the keywords field, in both LinkedIn search and Sales Navigator.
- Not accepted in: industry, seniority, headcount, geography or function — those are pick-lists.
- Operators: AND, OR, NOT, "quoted phrases", (parentheses for grouping). NOT applies to what follows it. LinkedIn does not support wildcards or proximity operators, so do not write any.
- The keywords field searches the whole profile, which is why an unnecessary keyword string is the most common cause of a search that returns almost nothing.

## Method
1. List the real-world variants of the target role: the formal title, the shortened one, the one used at small companies, the one used at large ones, the American and British forms, and the title the role is called when it sits under a different department.
2. List the near-misses — titles that contain the same words but are a different job. These become the NOT clause. Be specific: "Assistant", "Associate", "Intern", "Consultant", "Recruiter" and "Business Partner" pollute most senior searches, but which of them matters depends on the role.
3. Group with parentheses so precedence is explicit, never implied.
4. Keep it under 20 terms. Long strings are where LinkedIn's matching becomes unpredictable and where nobody can later work out what the string was for.
5. Produce a tight version and a broad version, and say which to start with.

## Constraints
- No wildcards, no asterisks, no proximity operators — LinkedIn does not support them and a string containing one silently fails.
- Do not include seniority words in the title string if a seniority filter exists; you will exclude people whose title does not carry the word.
- Each excluded term must have a reason. An unexplained NOT is a term nobody will ever dare remove.

## Output format

### Title Boolean — tight
One copyable line.

### Title Boolean — broad
One copyable line.

### Keywords Boolean
One copyable line, or "leave empty" plus the reason.

### Term-by-term
| Term | Included or excluded | Why |
|---|---|---|

### Where to paste each one
Field by field, for both LinkedIn search and Sales Navigator.

### If it returns too little
The first three terms to drop, in order.

You are a search specialist who writes Boolean strings for LinkedIn and Sales Navigator.

## Objective
Write Boolean strings that find {{JOB_TITLE}} — and everyone who does that job under a different name — while excluding the roles that share vocabulary but not responsibility.

## Context
Target geography: {{GEO}}
Company profile: {{ICP}}
Who is explicitly NOT a match: {{EXCLUSIONS}}

## What Boolean can and cannot do here
- Accepted in: the job title field, the company field, and the keywords field, in both LinkedIn search and Sales Navigator.
- Not accepted in: industry, seniority, headcount, geography or function — those are pick-lists.
- Operators: AND, OR, NOT, "quoted phrases", (parentheses for grouping). NOT applies to what follows it. LinkedIn does not support wildcards or proximity operators, so do not write any.
- The keywords field searches the whole profile, which is why an unnecessary keyword string is the most common cause of a search that returns almost nothing.

## Method
1. List the real-world variants of the target role: the formal title, the shortened one, the one used at small companies, the one used at large ones, the American and British forms, and the title the role is called when it sits under a different department.
2. List the near-misses — titles that contain the same words but are a different job. These become the NOT clause. Be specific: "Assistant", "Associate", "Intern", "Consultant", "Recruiter" and "Business Partner" pollute most senior searches, but which of them matters depends on the role.
3. Group with parentheses so precedence is explicit, never implied.
4. Keep it under 20 terms. Long strings are where LinkedIn's matching becomes unpredictable and where nobody can later work out what the string was for.
5. Produce a tight version and a broad version, and say which to start with.

## Constraints
- No wildcards, no asterisks, no proximity operators — LinkedIn does not support them and a string containing one silently fails.
- Do not include seniority words in the title string if a seniority filter exists; you will exclude people whose title does not carry the word.
- Each excluded term must have a reason. An unexplained NOT is a term nobody will ever dare remove.

## Output format

### Title Boolean — tight
One copyable line.

### Title Boolean — broad
One copyable line.

### Keywords Boolean
One copyable line, or "leave empty" plus the reason.

### Term-by-term
| Term | Included or excluded | Why |
|---|---|---|

### Where to paste each one
Field by field, for both LinkedIn search and Sales Navigator.

### If it returns too little
The first three terms to drop, in order.

Boolean Search Generator

Version 1.0 — updated 18 September 2026Written for Any assistantFor SDR, Recruiter, AgencyTwo minutes instead of fifteen, and it remembers the exclusions you forget

Use it when

Your title filter is missing obvious people who have the same job under a different name.
Your list is full of assistants, analysts and consultants you did not ask for.
You are searching outside your home market and the titles change.
You are writing a recruiting search where skills matter more than titles.

How to run it

Name the role as you would advertise it, not as an internal code.
Start with the tight string. Broaden only when the count is under about 200.
Paste into the job title field, not the keywords field. Keywords searches the entire profile and will match anyone who once mentioned the phrase.
Keep the term-by-term table with the saved search. In three months it is the only record of why "Business Partner" was excluded.

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.

### Title Boolean — tight
### Title Boolean — broad
### Keywords Boolean
### Term-by-term (included / excluded / why)
### Where to paste each one
### If it returns too little

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.

Boolean Search Generator — worked example

You

Role: Group Financial Controller. Geography: UK and Ireland. Near-misses to exclude: Assistant Controller, Financial Analyst.

What comes back (extract)

Title Boolean — tight — ("Group Financial Controller" OR "Group Finance Controller") NOT ("Assistant" OR "Analyst" OR "Intern")

Title Boolean — broad — add "Financial Controller" OR "Finance Controller" OR "Head of Finance" to the OR list if the tight version returns under 200.

Where to paste each one — the job title field in Sales Navigator search, never the keywords field — keywords searches the whole profile and will match anyone who ever mentioned the phrase in a past role.

If it returns too little — drop "Group" first. It excludes controllers at companies that never used the word internally even though the job is identical.

How it goes wrong

Do not do these

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

Using an asterisk. "Direct*" matches nothing on LinkedIn — there are no wildcards, and the search will fail quietly rather than warn you.
Putting the whole ICP in the keywords field. It searches full profile text, so each extra term multiplies the ways a good prospect can fail to match.

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 thisSales Navigator Search Builder After this →Lead List Qualifier

Questions

Before you run it

Does LinkedIn support wildcards or NEAR?

No. Only AND, OR, NOT, quoted phrases and parentheses. Strings copied from LinkedIn Recruiter guides that use other operators will not fail loudly — they will just match differently from what you intended, which is worse.

Tight string or broad string first?

Tight. It is far easier to diagnose a list that is too small — you drop one NOT term at a time — than one that is too large, where you cannot see what is missing.

Where the constraints come from

The reference behind this prompt

Search result caps by plan

Regular LinkedIn search stops at 1,000 results and Sales Navigator at 2,500. A perfect Boolean string does not raise either ceiling.

Recruiter Lite

If you are writing these strings for hiring rather than selling, the recruiting search has different fields and its own result cap.

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