Boolean search strings for hard-to-find candidates
Finding the right people in LinkedIn Recruiter, an ATS, or a Google X-ray means writing Boolean strings full of title variants, skill synonyms, and exclusions — tedious to build and easy to get subtly wrong. Automating candidate search is a core AI use (about 32% of teams), and this is a task AI does genuinely well: it generates and explains the strings so you can tune them by hand.
You are a sourcing expert who writes and explains Boolean search strings for a recruiter. I will describe the role; you give me strings I can tune. Role and core skills: {{role_and_skills}} Must-haves vs. nice-to-haves: {{must_have_vs_nice}} Where I am searching (LinkedIn Recruiter, ATS, Google X-ray, etc.): {{platform}} Titles, companies, or terms to exclude: {{exclusions}} Return: 1. Three Boolean strings — one tight (high precision), one broad (high recall), and one in the middle — ready to paste, using AND / OR / NOT and quotation marks correctly for the platform I named. 2. A plain-English note on what each string will over- or under-match, so I know which to reach for. 3. A synonyms-and-variants list: alternate job titles, adjacent skills, and common misspellings I should consider adding or removing. Rules: tailor the syntax to the platform I gave you and flag anything that platform does not support (LinkedIn ignores parentheses; a Google X-ray needs a site: operator). Do not claim a string will find a specific number of people or specific individuals — these are starting points I will test and refine. If the role is too vague to search well, tell me exactly what to specify.
Fill in your details and the prompt updates live — then copy.
Tight (high precision): "platform engineer" AND Kubernetes AND Go AND (Terraform OR "infrastructure as code") NOT (recruiter OR student OR aspiring) Broad (high recall): (Kubernetes OR k8s) AND (Go OR Golang OR "site reliability" OR SRE OR "platform") What each matches: the tight string will miss people who list "k8s" or "SRE" instead of the full titles; the broad one will pull in SREs who may not do platform work — skim titles before you message. Variants to try: k8s, EKS, GKE, "cloud native," Golang, SRE, "DevOps engineer."
The full workflow
- Describe the role in skills, not just a title, so the synonyms come out useful.
- Paste the middle string first, then widen or tighten based on what comes back.
- Skim the actual results — a string is a net, not a verdict.
- Save the strings that work per role type so the next req starts from a template.
Watch out for
Do not filter on proxies for protected characteristics — graduation year, a specific decade of experience, women's-college names, or a neighborhood can create age or other disparate-impact exposure. Search on skills, not stand-ins for who a person is.
The string finds profiles that match words, not people who fit the job. Verify every match yourself; do not treat search rank as a screening decision.
Where this comes from
Every use case on this site is grounded in real reports from working recruiters — not invented by us.