Uniqueness Engine: Verified Personal Facts on People

Hobbies, causes, fandom, and milestones. Each line is a quote with a source.

Everyone already has the job title. This finds the person: the marathon PR, the rescue dog's name, the team they've had season tickets for since college, the food bank board they sit on. Every fact comes with the source URL and the exact quote. If we can't quote it, you don't get it.

You tell us who with a LinkedIn profile URL, because this is built for B2B. The research runs across the public web (their blog, podcasts, race results, press, posts), not just LinkedIn. No cookies, no login.

If we can't confirm it's the right person, or we find no verified personal fact, nothing is delivered and you pay $0.

Built on Uniqueness Engine.

Personal facts vs profile scrapers

	First line of a cold email
From scraper data (what every other sender already has)	"Hi Jane, I came across your profile and saw you're VP of Engineering at Acme…"
From a sourced personal fact	"Hi Jane, saw Banjo already runs the house. Anyone who adopts a third rescue is someone I want to talk to about long-horizon work."

The second line uses personal_hook: a cited fact you can open and check before you send.

What we look for

What they do Marathons and PRs, half marathons, triathlons, cycling, golf, tennis, rec leagues, hiking, climbing, fishing, skiing, cooking, baking, gardening, video games, chess and board games, instruments, bands, photography, painting, writing, collecting.

What they like Books they're reading, film and TV, music they love, concerts, food they prefer, drinks they order, restaurants, bars, hotels, venues, destinations, brands, products and snacks, cars and style.

Who they root for Professional teams, college teams, season tickets, school teams they played on, alma mater, fraternity or sorority, hometown.

Causes, pets, and the rest of life Pets, rescue animals, volunteering, nonprofit boards, charity walks, community clubs, youth sports coaching, moves, awards, certifications, travel, origin story, personal philosophy, things they avoid, shows they make, books they wrote, family (only when they say it themselves).

That's the map, not a limit. Falconry, speedcubing, competitive BBQ judging and restoring pinball machines turn up the same way: if it's public and quotable, it counts.

GDPR special-category facts (health, religion, politics, and similar) are excluded on this actor.

How it works

1. Identity. Name, photo, handles, and links have to match the person at the URL. Same-name strangers are dropped.
2. Quote. Every fact needs public text we can quote, with the link.
3. Second check. A separate pass confirms the quote is about this person and says what the fact claims.

No match, or no verified personal fact: needs_review, nothing delivered, $0.

Each personal fact carries attribution: self_stated (their own words) or reported (published by someone else about them). Personal-looking rows that fail the checks are dropped, not sold.

Live example: Bill Gates

From a Uniqueness Engine brief for https://www.linkedin.com/in/williamhgates/ (2026-09-24, 47 verified personal facts; a few below):

Fact	Quote	Attribution
Plays bridge, especially with Warren Buffett	"My parents first taught me bridge, but I really started to enjoy it after playing with Warren Buffett."	self_stated
Played tennis his whole life, including a match with Roger Federer	"I have played tennis my whole life. This year, I got to play a match with Roger Federer to help raise money for his foundation."	self_stated
Settlers of Catan is the family board game	"This civilization-building board game is a favorite in my family."	self_stated
Reads about a book a week	"On average, I try to read a book a week, and I always bring a whole tote bag of them on vacation."	self_stated
Plays pickleball	"I've been playing pickleball for 50 years"	reported

personal_hook for that run: "Bill Gates published a memoir titled Source Code."

Demo fixture: Jordan Ellis (Banjo)

The demo on uniquenessengine.com is a labeled fictional fixture. It shows the kind of fact that makes a first line:

• "Just adopted a third rescue dog, Banjo." Quote: "adopted our third rescue this weekend — Banjo already runs the house 🐶"
• "Lifelong Buffalo Bills fan." Quote: "Bills Mafia for life. Through every single heartbreak."
• "Ran the Chicago Marathon for the third time, a 3:48 PR."

"Interested in dogs, sports, fitness" is a segment. "Banjo already runs the house" is a first sentence you can send.

How to run it

1. Paste one LinkedIn profile URL per person into linkedinUrls. The URL is how we identify them.
2. Run. Research takes about 45 to 90 seconds per person. A batch of ten runs in parallel, so it is not ten times as long.
3. Export the dataset (JSON, CSV, Excel, or the Apify API) and drop personal_hook into your sequencer.

No LinkedIn account, cookies, or credentials are ever requested.

Input

{
    "linkedinUrls": ["https://www.linkedin.com/in/williamhgates/"],
    "maxUrls": 10
}

• linkedinUrls: LinkedIn people-profile URLs (linkedin.com/in/...), used to identify each person. Company pages are not supported.
• maxUrls: default 10, max 100. Caps spend up front.

Output

Each delivered brief is one dataset item. Refused and skipped profiles are listed with reasons in the run summary (key-value store OUTPUT). They are never in the dataset and never charged. A brief is delivered only when it has at least one verified personal fact.

OUTPUT has delivered, refused[], skipped[] (each with a reason), and chargedEventCounts, the number of billable briefs in this run (one per dataset item).

Flat field	What it holds
personal_hook	Best verified personal line, ready for a first sentence
interest_1, interest_2	Labels of the top personal facts
source_1, quote_1	Source URL + exact quote behind the hook
safe_to_reference	Personal facts joined with |
identity_confidence	0 to 1 confidence the brief belongs to the right person
status	ok on delivered items

Dataset items also include personalFacts[] / professionalFacts[] with {fact, sourceUrl, quote} (personal facts add attribution), plus fullName, company, title, and discoveredHandles.

giftIdeas and outreachAngles are always empty. The engine returns facts, not copy.

Example dataset item (live actor run, truncated)

{
    "status": "ok",
    "sourceProfileUrl": "https://www.linkedin.com/in/williamhgates/",
    "fullName": "Bill Gates",
    "company": "Gates Foundation",
    "title": "Chair, Gates Foundation and Founder, Breakthrough Energy",
    "identityConfidence": 0.9,
    "personal_hook": "Bill Gates has a deep friendship with Warren Buffett.",
    "interest_1": "Friendship with Warren Buffett",
    "source_1": "https://www.linkedin.com/feed/update/urn:li:activity:7499851762841927680/",
    "quote_1": "It was a deep friendship from our very first conversation.",
    "personalFacts": [
        {
            "fact": "Bill Gates has a deep friendship with Warren Buffett.",
            "sourceUrl": "https://www.linkedin.com/feed/update/urn:li:activity:7499851762841927680/",
            "quote": "It was a deep friendship from our very first conversation.",
            "attribution": "self_stated"
        },
        {
            "fact": "Bill Gates first learned about computers at age 13.",
            "sourceUrl": "https://gatesnot.es/AI",
            "quote": "When I first learned about computers at age 13",
            "attribution": "self_stated"
        },
        {
            "fact": "Bill Gates is a voracious reader.",
            "sourceUrl": "https://www.linkedin.com/in/williamhgates/",
            "quote": "Voracious reader.",
            "attribution": "reported"
        }
    ]
}

How much does it cost?

$0.37 per delivered brief. Same unit price as uniquenessengine.com. One dataset item = one charge. Refused, failed, and skipped profiles, and briefs with no verified personal fact, are free. maxUrls (default 10, max 100) caps every run.

This is research-grade enrichment, not a profile scrape. You pay only when a sourced brief is delivered.

Who uses it

• Sales / SDR / GTM: personalize cold email and LinkedIn outreach with a sourced hobby, not a job title everyone already has.
• Clay / Instantly / Smartlead: map personal_hook into a sequencer variable; skip rows with no dataset item.
• Founders: research investors, partners, and dream customers before the first touch.
• CS / CX / account teams: call prep and mid-funnel notes from public interests and causes.
• AI agents: research the person before drafting outreach; every fact has a URL a human can open.

Integrations

Clay

POST https://api.apify.com/v2/acts/greg_benbetter~uniqueness-engine/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>
Content-Type: application/json
{ "linkedinUrls": ["{{LinkedIn Profile URL}}"], "maxUrls": 1 }

Map personal_hook, interest_1, source_1. Branch on whether a row was returned. Refused profiles produce no dataset item and cost nothing.

Instantly / Smartlead

Export CSV and import personal_hook / interest_1 as custom variables.

n8n / Make / Apify API

Webhook on ACTOR.RUN.SUCCEEDED, or call the actor via the Apify API / MCP.

Responsible use

• Public data only. Every fact cites the page and quote it came from.
• You are the controller of your use (GDPR/CCPA, CAN-SPAM, PECR).
• Not a consumer report. Do not use for employment, credit, housing, insurance, or FCRA purposes.
• Do not use for spam, harassment, stalking, or doxxing.

Data-deletion requests: uniquenessengine.com.

FAQ

Is this a LinkedIn scraper? No. Scrapers extract fields already on the profile. This researches the person across public sources and returns only cited facts, refusing when it isn't sure.

What if you can't find the person? It refuses and you are not charged. Refused URLs appear in the run summary.

How long does a run take? About 45–90 seconds per profile (up to ~2–3 minutes). Batches run in parallel.

Does it need my LinkedIn cookies? No.

Does it write my emails? No. It returns verified facts; the words stay yours.

Built on Uniqueness Engine. Issues and data-deletion requests go there.