People Data Labs connector for AI agents

Tools your data enrichment agent reaches for on People Data Labs, scoped per user.

CALL ANY TOOL

14 tools for data enrichment in People Data Labs: enrich people, companies, IPs, and job titles, run bulk enrichment of up to 100 records, search people, companies, and job postings, and clean messy names and locations.

peopledatalabs_autocomplete

Autocomplete

Suggest valid People Data Labs values for a field, such as company, school, title, skill, industry or location, from a text prefix. Returns data, an array of suggestions each with name, count and meta (extra details that depend on the field), sorted by most common first. Use autocomplete to find exact values before building search_people or search_companies queries. Use clean_company, clean_school or clean_location to normalize one known input. Provide the field input.

Parameters

Name

Type

Required

Description

field

string

Required

The field to suggest values for. One of all_location, class, company, country, industry, location_name, major, region, role, school, sub_role, skill, title, website. One of: `all_location`, `class`, `company`, `country`, `industry`, `location_name`, `major`, `region`, `role`, `school`, `sub_role`, `skill`, `title`, `website`.

size

integer

Optional

Number of suggestions to return, from 1 to 100. Defaults to 10.

text

string

Optional

Starting text to complete, e.g. goog. An empty value returns the most common values.

titlecase

boolean

Optional

When true, text in the response is titlecased instead of the default lowercase.

peopledatalabs_bulk_enrich_companies

Bulk enrich companies

peopledatalabs_bulk_enrich_persons

Bulk enrich persons

peopledatalabs_clean_company

Clean company

peopledatalabs_clean_location

Clean location

peopledatalabs_clean_school

Clean school

peopledatalabs_enrich_company

Enrich company

Find the single best-matching company profile for a name, website, LinkedIn URL, ticker or PDL ID. Returns likelihood (1 to 10) and the full company profile fields such as size, industry, location, funding and social URLs; a 404 means no match was found and is not charged. Use enrich_company for one known company. Use search_companies to find companies by criteria, or clean_company to only normalize a company name or URL. Provide at least one of pdl_id, name, ticker, website or profile.

Parameters

Name

Type

Required

Description

country

string

Optional

Country of the company HQ, e.g. United States.

data_include

string

Optional

Comma-separated list of fields the response should include; use dot notation for subfields. Start with - to exclude fields instead. Example: name,location.metro

include_if_matched

boolean

Optional

When true, the response lists which of the request inputs matched this company.

locality

string

Optional

City of the company HQ, e.g. Mountain View.

location

string

Optional

Location of the company's headquarters, from street address to country, e.g. 1600 Amphitheatre Pkwy, Mountain View, CA 94043.

min_likelihood

integer

Optional

Minimum likelihood score (1 to 10) for a company to count as a match. Default is 2; use 6 or more for high precision.

name

string

Optional

The company's name, e.g. Google, Inc.

pdl_id

string

Optional

PDL company ID or LinkedIn slug, e.g. aKCIYBNF9ey6o5CjHCCO4goHYKlf or google. When set, other match inputs are ignored.

postal_code

string

Optional

Postal code of the company HQ, e.g. 94043.

profile

string

Optional

The company's social profile URL, e.g. linkedin.com/company/google.

region

string

Optional

State or region of the company HQ, e.g. California.

required

string

Optional

Boolean expression of top-level company fields a match must contain, so you are only charged for useful matches. Example: location AND (website OR linkedin_url)

street_address

string

Optional

Street address of the company HQ, e.g. 1600 Amphitheatre Pkwy.

ticker

string

Optional

Stock ticker of a publicly traded company, e.g. GOOGL.

titlecase

boolean

Optional

When true, text in the response is titlecased instead of the default lowercase.

website

string

Optional

The company's website, e.g. google.com.

peopledatalabs_enrich_ip

Enrich ip

peopledatalabs_enrich_job_title

Enrich job title

peopledatalabs_enrich_person

Enrich person

Find the single best-matching person profile for the identifying details you provide, such as an email, LinkedIn URL, phone number, or name plus company. Returns likelihood (1 to 10) and a data object with the full person profile; a 404 means no match was found and is not charged. Use enrich_person for one known person. Use identify_person to get several candidate profiles from partial details, or search_people to find people by criteria. Provide at least one of profile, email, phone, email_hash, lid, pdl_id, or a name together with company, school or location.

Parameters

Name

Type

Required

Description

birth_date

string

Optional

The person's birth year or full birth date as YYYY-MM-DD, e.g. 1996-10-01.

company

string

Optional

Name, website or social URL of a company where the person has worked, e.g. Amazon.

country

string

Optional

Country where the person lives, e.g. United States.

data_include

string

Optional

Comma-separated list of fields the response should include; use dot notation for subfields. Start with - to exclude fields instead. Example: full_name,emails.address

string

Optional

An email address the person has used, e.g. sean.thorne@talentiq.co.

email_hash

string

Optional

SHA-256 or MD5 hash of an email address the person has used.

first_name

string

Optional

The person's first name, e.g. Jennifer. Use together with last_name.

include_if_matched

boolean

Optional

When true, the response lists which of the request inputs matched this profile.

last_name

string

Optional

The person's last name, e.g. Jackson. Use together with first_name.

lid

string

Optional

The person's numeric LinkedIn ID, e.g. 145991517.

locality

string

Optional

City or locality where the person lives, e.g. Boise.

location

string

Optional

Where the person lives. Anything from a street address to a country name, e.g. Medford, OR USA.

middle_name

string

Optional

The person's middle name, e.g. Cassandra.

min_likelihood

integer

Optional

Minimum likelihood score (1 to 10) for a profile to count as a match. Default is 2; use 6 or more for high precision.

name

string

Optional

The person's full name, at least first and last, e.g. Jennifer C. Jackson. Needs another field such as company, school or location to match.

pdl_id

string

Optional

PDL persistent ID of a person record, e.g. qEnOZ5Oh0poWnQ1luFBfVw_0000. When set, the other match inputs are ignored.

phone

string

Optional

A phone number the person has used. Must begin with +[country code], e.g. +1 555-234-1234.

postal_code

string

Optional

Postal code where the person lives, e.g. 83701. Assumed to be US when country is empty.

profile

string

Optional

A social profile URL the person has used, e.g. https://linkedin.com/in/seanthorne.

region

string

Optional

State or region where the person lives, e.g. Idaho.

required

string

Optional

Boolean expression of top-level fields a match must contain, so you are only charged for useful matches. Example: education AND (emails OR phone_numbers)

school

string

Optional

Name, website or social URL of a school the person attended, e.g. University of Iowa.

street_address

string

Optional

Street address where the person lives, e.g. 1234 Main Street.

titlecase

boolean

Optional

When true, text in the response is titlecased instead of the default lowercase.

peopledatalabs_identify_person

Identify person

Find up to 20 candidate person profiles that match broad identifying details such as a name, company, school or street address. Returns a matches array of profiles, each with a match_score (1 to 99) and its data; one credit is used per call however many profiles return. Use identify_person when the details cannot pin down one person. Use enrich_person for a unique match, or search_people for criteria-based queries. Provide at least one of profile, email, phone, email_hash, lid, name, company, school, location, street_address, locality, region or postal_code.

Parameters

Name

Type

Required

Description

birth_date

string

Optional

The person's birth year or full birth date as YYYY-MM-DD, e.g. 1996-10-01.

company

string

Optional

Name, website or social URL of a company where the person has worked, e.g. Amazon.

country

string

Optional

Country where the person lives, e.g. United States.

data_include

string

Optional

Comma-separated list of fields the response should include; use dot notation for subfields. Start with - to exclude fields instead. Example: full_name,emails.address

string

Optional

An email address the person has used, e.g. sean.thorne@talentiq.co.

email_hash

string

Optional

SHA-256 or MD5 hash of an email address the person has used.

first_name

string

Optional

The person's first name, e.g. Jennifer. Use together with last_name.

include_if_matched

boolean

Optional

When true, the response lists which of the request inputs matched this profile.

last_name

string

Optional

The person's last name, e.g. Jackson. Use together with first_name.

lid

string

Optional

The person's numeric LinkedIn ID, e.g. 145991517.

locality

string

Optional

City or locality where the person lives, e.g. Boise.

location

string

Optional

Where the person lives. Anything from a street address to a country name, e.g. Medford, OR USA.

middle_name

string

Optional

The person's middle name, e.g. Cassandra.

name

string

Optional

The person's full name, at least first and last, e.g. Jennifer C. Jackson. Needs another field such as company, school or location to match.

phone

string

Optional

A phone number the person has used. Must begin with +[country code], e.g. +1 555-234-1234.

postal_code

string

Optional

Postal code where the person lives, e.g. 83701. Assumed to be US when country is empty.

profile

string

Optional

A social profile URL the person has used, e.g. https://linkedin.com/in/seanthorne.

region

string

Optional

State or region where the person lives, e.g. Idaho.

school

string

Optional

Name, website or social URL of a school the person attended, e.g. University of Iowa.

street_address

string

Optional

Street address where the person lives, e.g. 1234 Main Street.

titlecase

boolean

Optional

When true, text in the response is titlecased instead of the default lowercase.

peopledatalabs_search_companies

Search companies

peopledatalabs_search_job_postings

Search job postings

Search People Data Labs job postings using field filters such as company, title, location, salary and skills, or a raw Elasticsearch query. Returns data (an array of job posting records, newest first), total matches, scroll_token and dataset_version; each record uses one credit. Use search_job_postings to find open roles or hiring signals. Use search_companies for company records and enrich_company for one company. Provide at least one field filter or a query; query overrides the field filters. This API is in beta.

Parameters

Name

Type

Required

Description

company_id

string

Optional

PDL company ID of the hiring company, e.g. LGrXE14x4Kvzj2cbaeRUngOCTuJA.

company_industry

string

Optional

Industry of the hiring company, e.g. computer software.

company_industry_v2

string

Optional

Version 2 industry of the hiring company, e.g. software development.

company_name

string

Optional

Hiring company name (cleaned, exact match), e.g. anthropic.

company_profile

string

Optional

Hiring company LinkedIn profile URL, e.g. linkedin.com/company/amazon.

company_website

string

Optional

Hiring company website (cleaned, exact match), e.g. amazon.com.

deactivated_date_max

string

Optional

Latest deactivated date, YYYY-MM-DD inclusive, e.g. 2026-01-31.

deactivated_date_min

string

Optional

Earliest deactivated date, YYYY-MM-DD inclusive, e.g. 2026-01-01.

description

string

Optional

Text to find in the job description, e.g. LLM.

first_seen_max

string

Optional

Latest date PDL first saw the posting, YYYY-MM-DD inclusive, e.g. 2026-01-31.

first_seen_min

string

Optional

Earliest date PDL first saw the posting, YYYY-MM-DD inclusive, e.g. 2026-01-01.

string

Optional

PDL persistent job posting ID, e.g. +/vVJ9lbrec.

inferred_skills

string

Optional

Skill inferred from the posting description, e.g. javascript.

is_active

boolean

Optional

true returns only active postings, false returns only deactivated postings.

last_verified_max

string

Optional

Latest last-verified date, YYYY-MM-DD inclusive, e.g. 2026-01-31.

last_verified_min

string

Optional

Earliest last-verified date, YYYY-MM-DD inclusive, e.g. 2026-01-01.

location

string

Optional

Any location of the posting: street address, city, region, country or postal code, e.g. united states.

query

object

Optional

Elasticsearch (v7.7) query object over job posting fields. When set, all field filters are ignored. Example: {"bool": {"must": [{"term": {"company_name": "anthropic"}}]}}

remote_work_policy

string

Optional

Remote work policy of the posting, e.g. Remote.

salary_currency

string

Optional

Currency code of the listed salary, e.g. usd.

salary_period

string

Optional

Pay period of the listed salary, e.g. annual.

salary_range_max

integer

Optional

Maximum listed salary; returns postings at or below this value, e.g. 200000.

salary_range_min

integer

Optional

Minimum listed salary; returns postings at or above this value, e.g. 100000.

scroll_token

string

Optional

Pagination token from the previous response's scroll_token. Send the same query with this token to fetch the next batch.

size

integer

Optional

Maximum number of postings to return, from 1 to 100. Defaults to 10; each record uses one credit.

title

string

Optional

Job title to match (cleaned, phrase match), e.g. data engineer.

title_class

string

Optional

PDL job class of the posting, e.g. research_and_development.

title_levels

string

Optional

PDL seniority level of the posting, e.g. senior.

title_role

string

Optional

PDL job role of the posting, e.g. engineering.

title_sub_role

string

Optional

PDL job sub-role of the posting, e.g. data_engineering.

peopledatalabs_search_people

Search people

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// People Data Labs tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["peopledatalabs"], toolNames: [
    "peopledatalabs_enrich_person",
    "peopledatalabs_enrich_company",
    "peopledatalabs_search_people"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Enrich jane.doe@contoso.com and her company" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["peopledatalabs"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Enrich jane.doe@contoso.com and her company" }],
  tools,
});

// Execute the tool call with the user's vaulted People Data Labs API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["peopledatalabs"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Enrich jane.doe@contoso.com and her company" }],
  tools,
});

// Tool call runs with the user's vaulted People Data Labs API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["peopledatalabs"] }, pageSize: 100,
});

const agent = new Agent({
  name: "enrichment_agent",
  model: "gemini-2.5-pro",
  instruction: "People Data Labs tools scoped to this user",
  tools,
});

await agent.run("Enrich jane.doe@contoso.com and her company");

Try these prompts

Copy any prompt into your agent. Each maps directly to a People Data Labs tool. Click to copy, paste into your agent, done.

People

Copy the prompt

Copied

Enrich jane.doe@contoso.com.

Copy the prompt

Copied

Find candidate profiles for Sam Lee who went to Stanford.

Copy the prompt

Copied

Search for data engineers in Berlin who know Snowflake.

Companies

Copy the prompt

Copied

Enrich the company behind northwind.io.

Copy the prompt

Copied

Find fintech companies in New York with 200 to 500 employees.

Copy the prompt

Copied

Which company is behind this IP address?

Clean and normalize

Copy the prompt

Copied

Normalize the job title sr. swe and list related titles.

Copy the prompt

Copied

Clean up this company name: Contoso Intl. Ltd.

Copy the prompt

Copied

Suggest skill values that start with machine lea.

SEE HOW AUTH WORKS

Each user connects their own People Data Labs API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

People Data Labs

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

People Data Labs

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

People Data Labs

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

People Data Labs

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other sales and search connectors.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared People Data Labs API key looks fine in a demo. In production every enrichment looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

People Data Labs today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access People Data Labs as the user or through a shared API key?

As the user. Each user connects their own People Data Labs API key once, and Scalekit sends it with every call. Audit logs attribute every enrichment and search to that user, not a shared service account.

Where is the People Data Labs API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in People Data Labs?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example single enrichment without the bulk tools, which enrich up to 100 records per call. Every People Data Labs tool is read-only, so the agent cannot change data in the account. Scalekit also enforces scope checks before every API call.

What happens when a user revokes People Data Labs access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

What does the agent get when People Data Labs finds no match?

peopledatalabs_enrich_person returns the single best match with a likelihood score from 1 to 10. A 404 means no match was found, and it is not charged. For partial details, peopledatalabs_identify_person returns up to 20 candidate profiles.