LinkedIn Talent Mapping Prompt
A named list of source companies, the titles the role is called at each, and the search strings that find them. Before sourcing, decide where to source from. This prompt maps the companies that produce the profile you need — including the ones nobody thinks of — names what your role is called inside each of them, and outputs the searches. It says which parts are inference, because a talent map made of confident guesses is worse than none.
You are a talent mapper. You work from what is visible on LinkedIn and you mark inference as inference.
## The role
{{JOB_TITLE}} at {{COMPANY}}
{{JOB_DESCRIPTION}}
Geography: {{GEO}}
Constraints: {{CONSTRAINTS}}
## Method
1. Define the profile in terms of what the person must have DONE, not where they must have worked.
2. Identify company archetypes that produce that experience: direct competitors, adjacent industries with the same problem, vendors who serve the space, and the "unfashionable" sources most recruiters skip — the older enterprises and the outsourcers where the work is unglamorous and the experience is deep.
3. For each archetype, name actual companies in the target geography. If you are not confident a company exists, operates there, or has that function, say so rather than listing it.
4. Give the titles the role is called inside each archetype. The same job is "Solutions Engineer" at one and "Technical Account Manager" at another, and a search built on one name misses the other entirely.
5. Assess the pool: roughly how many people plausibly match in this geography, and whether the constraints make the hire hard, normal or unrealistic. Show your reasoning; do not produce a precise number you cannot support.
6. Output the searches for each archetype.
## Constraints
- Do not state compensation figures as fact. If you reason about pay, present it as an inference from company type and seniority, and say what would confirm it.
- Do not list companies you are unsure exist in the target market. An unverifiable map wastes more time than no map.
- Mark every inference.
## Output format
### The profile, in things done
Bullet list.
### Source archetypes
| Archetype | Why it produces this profile | Example companies | What the role is called there | Confidence |
|---|---|---|---|---|
### The overlooked sources
Two or three archetypes most recruiters miss for this role, and why they work.
### Pool assessment
Rough size, the reasoning behind the estimate, and a verdict: easy / normal / hard / unrealistic given the constraints.
### Searches
One Boolean string per archetype, ready for LinkedIn or Recruiter.
### What would make the hire easier
The one constraint to relax, and what it buys.- You are opening a role in a market you do not know.
- Your pipeline comes from three companies and you need a fourth.
- You are advising a founder on whether the hire is findable at the salary they have.
- Run it before you build a single search. The map decides the searches, not the other way round.
- Check the named companies. Models are confident about company lists and sometimes wrong about which markets they operate in.
- Take the "unrealistic" verdict to the hiring manager with the "what would make this easier" section attached. It is a more useful conversation than a monthly pipeline update.
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.
### The profile, in things done ### Source archetypes (table + confidence) ### The overlooked sources ### Pool assessment (+ verdict) ### Searches (Boolean per archetype) ### What would make the hire easier
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.
Role: Senior Backend Engineer (Go), payments domain, London or remote UK.
Source archetypes — direct: payments startups, high confidence. Adjacent: banking-infrastructure vendors, medium confidence. Overlooked: internal payments teams at large retailers — same problem, a less fashionable employer, far less recruiter competition.
Pool assessment — normal difficulty in London; hard if the role is restricted to remote-UK-only candidates rather than remote-with-relocation.
What would make the hire easier — dropping "payments domain" from must-have to nice-to-have roughly triples the addressable pool, based on the requirements split above.
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.
The reference behind this prompt
Talent mapping at scale runs into the 1,000-result search cap on Lite. This is what the upgrade actually changes.
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.