nvNeuralVerge
Data Sources

Building a Sales Intelligence Agent

A tour of NeuralVerge's contact and company sources — email and phone enrichment, the email finder, LinkedIn endpoints and Crunchbase — and how an agent chains them.

Published September 23, 2026

An agent that is supposed to reach a person needs three things in a specific order: a way to resolve who that person is, a way to reach them, and enough company context to make the outreach worth sending. NeuralVerge answers all three from the same catalog, through the same request format: email enrichment and the email finder for contact resolution, phone enrichment for a second channel, LinkedIn's five lookups for identity and company signals, and Crunchbase company for funding. This post is a tour of those sources — what each one takes, what it returns, and which one to reach for first when you only have a name, a domain, or a company.

The four building blocks

Every one of these sources answers a different question, and knowing which question you're actually asking decides which call you make.

  • —Email enrichment and the email finder resolve a person's email address — one starting from an address you already have, the other starting from a name and a domain.
  • —Phone enrichment does the same job for a phone number, worldwide or US-specific.
  • —LinkedIn's lookups resolve identity and company data from a profile, a name, a domain or a search query — five distinct lookups for five distinct starting points.
  • —Crunchbase company adds funding and firmographic context once you know which company you're looking at.

None of these sources replace each other. An agent that needs to reach a named person at a known company typically touches at least three of them before it writes a message. Each one is read from the source at the moment the agent calls, not from a stored copy, and the same key also covers corporate registry records read with AI extraction and cited AI research for questions a record can't answer.

Email: two sources that answer different questions

Email finder: you have a name, you need an address

Email finder takes a first name, a last name and a company domain, and returns the resolved address with a confidence rating and a plain found flag. This is the call to make when a CRM record has a name and an employer but an empty email field.

curl -X POST https://api.neuralverge.ai/functions/v1/run-email-finder \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "first_name": "Jane", "last_name": "Example", "domain": "acme.example" }'

Email enrichment: you have an address, you need the person

Email enrichment runs the other direction: give it an address, and it returns full name, gender, phones, locations, company, position, work experience, and LinkedIn, X and Telegram handles where available. It solves the opposite problem to the finder — identification rather than discovery.

Email validation: check before you send

Email validation takes an address and returns deliverability signals. Run it on anything the finder returns before a large send, and on any address in a list you already hold that never passed through a finder. A confidence rating from the finder tells you how well an address is corroborated; validation tells you whether the mailbox will accept mail today. They are different questions, and conflating them is a common source of bounced mail.

Phone: enrich what you have, worldwide or US-specific

Phone enrichment takes a phone number and returns the same kind of profile as email enrichment — name, company, position, social handles — and works worldwide. Phone enrichment US is a specialized version for US numbers specifically, returning line type, carrier, a prepaid flag, an activity score and a litigator-risk flag. Reach for the worldwide source by default, and the US-specific one when that line-level detail matters for a given workflow.

LinkedIn: five lookups, five starting points

LinkedIn has five lookups because identity resolution has more than one entry point. Each of the five is its own dedicated endpoint. Here is what each lookup starts from:

  • —LinkedIn people profile + email — you have a profile URL and want the person's name, headline, location and about text, plus the email in the same call when one is available.
  • —LinkedIn profile by name and domain — you have a full name and a company name or domain, no profile link yet. This is usually the first LinkedIn call in a pipeline, since a name and an employer is what most intake records actually contain.
  • —LinkedIn people search — you don't have one person in mind; you want everyone matching a title, seniority, function or company filter. The widest filter set in the catalog — narrow filters keep the result relevant.
  • —LinkedIn company search — find companies by query, industry, size or location; each match comes back with industry, headquarters, follower count and a short description.
  • —LinkedIn company employee — search employees across one or more named companies at once, the shape you want when prospecting is scoped to a target account list rather than one company at a time.

The pattern across all five: start from whatever you already have — a URL, a name and a domain, or just a set of filters — and the matching lookup gets you the rest.

Crunchbase: the funding signal nothing else provides

Crunchbase company takes a Crunchbase company URL and returns total funding in US dollars, funding rounds with announcement date and type, investors with the round they appear on, founders, founding date, employee range, industries and a company description. Total funding is the field most go-to-market teams are actually after — the closest public proxy for whether a company can afford what you sell, and a newly funded company is one of the more reliable buying triggers in B2B. Pair it with LinkedIn company search, which returns industry, headquarters and a short description, and you have both how the company presents itself and what it has raised.

A worked example: resolving one person at Acme Oy (Finland)

Take an intake record with a name and an employer and nothing else: "Jane Example, Acme Oy, Finland."

  1. —LinkedIn profile by name and domain resolves the name and acme.example to a profile URL.
  2. —LinkedIn people profile + email reads that URL for headline, location and about text, and returns an email in the same call when one is available.
  3. —Email finder takes the first name, last name and domain and resolves a work address when the profile lookup came back without one, since a profile does not reliably expose an email.
  4. —Email validation checks the found address before it reaches a sending domain.
  5. —Crunchbase company resolves Acme Oy's funding history, so the brief can note whether the account raised recently.

Five calls, each answering one narrow question. The agent did not need to know in advance which source would succeed — it ran the sequence and recorded what came back, with each field tied to the call and session id that produced it.

One response shape across all of it

Every source in this tour answers in the same envelope: a session id, a kind naming the source with an echo of the request parameters, a readable human summary, and a structured machine object. An agent that has learned this shape from the email finder already knows how to read a Crunchbase or LinkedIn response — there is no per-source parsing logic to write. That consistency is the actual point of calling these sources through one catalog instead of five separate vendor integrations with five response formats.

Where teams use this combination

  • —Outbound list enrichment. Starting from a list of names and employers, resolve profiles, emails and company context in one pipeline before anything reaches a sequencer.
  • —CRM backfills. Nightly jobs that fill in missing email, phone or company fields on existing contacts.
  • —Lead scoring. Route inbound signups differently depending on company size, funding and seniority of the person who signed up.
  • —Account research ahead of a call. Pull the person's current role, the company's funding history and a validated contact method before a rep's first outreach.

What to check before you build on these sources

  • —Which starting point do you actually have? A name and a domain, a profile URL, or just a company — match it to the LinkedIn lookup built for that input instead of the one that happens to be top of mind.
  • —Do you validate before you send? A found or enriched email is a candidate, not a guarantee. Run it through validation before it reaches a sending domain you care about.
  • —Is the funding figure current enough for your use? Crunchbase profiles are read at request time but only as current as the profile itself — undisclosed rounds don't appear.

Frequently asked questions

Should I use the email finder or email enrichment?

It depends on what you start with. The email finder takes a first name, last name and company domain and resolves an address you don't have yet. Email enrichment takes an address you already have and returns the profile behind it. If the email field is empty, use the finder. If it's filled in and you want to know who it belongs to, use enrichment.

Do I need to validate an email after the finder returns one?

Yes, before any large send. A found address carries a confidence rating, not a deliverability guarantee. Email validation checks whether the mailbox is likely to accept mail right now, which is worth doing before it reaches a sending domain you care about.

Which LinkedIn endpoint do I call when I only have a name and a company?

LinkedIn profile by name and domain. It takes a full name and a company name or domain and resolves the matching profile, which is the usual starting point when a form or a CRM record gives you a person's name and employer but no direct link to their profile.

Can I get someone's email directly from their LinkedIn profile?

LinkedIn people profile plus email takes a profile URL and returns the email when one is available, in a single call. It is the fastest path when you already have the profile link and just need a way to reach the person.

What does Crunchbase add that LinkedIn and enrichment don't cover?

Funding. A Crunchbase company lookup returns total funding in US dollars, funding rounds with announcement date and type, founding date, employee range and industries from the company's Crunchbase profile — the closest public proxy for whether an account can afford what you sell, and a detail neither a LinkedIn profile nor a contact enrichment call provides.

About NeuralVerge

Give your agents structured, cited, real-world data from 150+ sources and the open web — through one API or MCP server.

Data Sources on the NeuralVerge blog.

Try it on your own data

One request format across research, extraction, and enrichment.

Get started