More Resources
Prompt

Enrich leads in ChatGPT with verified data

Tools: ChatGPT ▪ Lusha

Images and outputs on this page are for illustrative purposes only. The example below is a real result pulled live from Lusha, with personal details masked for privacy.

Most “enrich leads with ChatGPT” prompts are really research prompts, a summary, a guess at a title, nothing you can actually act on. Real enrichment means taking a partial record and filling it in with something current: verified email, direct phone, and the person’s actual company today, not whatever a search index still has cached. This play uses Lusha’s ChatGPT connector to do that directly.

How to set it up

01

Connect Lusha to ChatGPT

Open the , or add it from your connector settings directly.

02

Paste your partial list

Names, companies, old emails, whatever’s already in your CRM. The starting point doesn’t need to be complete.

03

Preview before you reveal

Confirm the matches look right first, search is far cheaper than reveal. Then reveal contact details only for the records you’ll actually use.

The prompt

Open in Claude Open in ChatGPT 

Here's a list of leads with name and company, some missing contact info: [paste list]. Use Lusha to find current work email and phone for each. Show me the matches first before revealing contact details.

What you'll get back

Real output, pulled live for this page. A search for sales contacts at Notion matched 695 people, here are two from the preview, before any reveal:

NameTitle (from search)Company (from search)
M H.Enterprise Sales ManagerNotion
L L.Sales ManagerNotion

Both show up under Notion in the initial search. Revealing them tells a different story:

NameCurrent titleCurrent companyEmailPhone
M H.Founding GTM Manager, Strategic Sales LeadA different company entirely, Notion shows only as previous employmentVerified work emailVerified mobile
L L.Sales ManagerNotion, confirmed currentVerified work emailVerified mobile + direct line

One of these two had already moved on. The search index still had him tagged at Notion; the reveal caught the actual, current employer. That’s the entire difference between research and enrichment in one real example: a record that looks fine until you check it.

Why use Lusha in ChatGPT

Ask ChatGPT to enrich this same list without Lusha connected, and it has nothing to check the Notion tag against. It would either say it can’t verify the current company, or it would repeat what your original list already said, which, as this example shows, would have been wrong for one of the two.

Connect Lusha, and enrichment stops being a guess dressed up as a data field. The model isn’t inferring who someone is now, it’s checking, and the check occasionally disagrees with what you started with. That disagreement is the useful part.

FAQ

  • Not reliably. Without one, it either says it can’t verify current details or produces something plausible that isn’t checked against anything real.

     

     

  • Preview first. Confirm the matches look right, then reveal only the records you’ll actually use.

  • A broad search can return a record’s last-known or historical association before the specific enrichment check confirms current employment. That’s exactly why previewing, then revealing, matters, the preview isn’t always the final answer.

Related Prompts

Ready to run this?

One data connection. Works in Claude, ChatGPT, your CRM, or any agent you build.

Start for free Read the Docs