More Resources
Prompt

Find lookalike companies to any account in Claude

Tools: Claude ▪ 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.

Your best accounts share a pattern, even if you haven’t named it yet. Ask Claude for companies that match a set of reference accounts, and Lusha’s lookalike model finds the pattern for you. This play uses Lusha’s Claude connector and lookalikes on top of verified company data.

How to set it up

01

Connect Lusha to Claude

Open the Lusha connector on Claude, or go to Settings → Connectors in Claude and add Lusha directly. Takes under a minute, no API key needed.

02

List your reference accounts

Give Claude 5 or more companies that represent the profile you’re looking for. More seeds, better matches.

03

Get matched companies back

Claude returns companies that match the underlying profile, sourced live from Lusha.

The prompt

Open in Claude Open in ChatGPT 

Find companies similar to [company name] and 4 more reference accounts in the same space. Return the top 10.


What you'll get back

Real output, pulled live for this page using Sn##flake and four other data-platform companies as reference accounts:

CompanyEmployeesLocation
C##tiveIQ1United States
So##lGPT2United States

 

Worth calling out honestly: this run matched Sn##flake against its data-platform peers, and the model surfaced early-stage companies working in the same space, not the household names you might expect. That’s the lookalike model doing its job, matching on underlying profile rather than brand recognition. If you want established, larger accounts specifically, pair this prompt with a company size filter.

 

Why use Lusha in Claude

Ask Claude the same question without Lusha connected, and it can only reason from what it already knows about a category, usually the same handful of well-known names anyone would guess. It has no way to find the companies nobody’s thought to check yet.

Connect Lusha, and the question runs against real company data. The lookalike model isn’t matching on brand recognition, it’s matching on the same underlying signals your best accounts share. That’s how it surfaces the companies a manual search would miss entirely.

This is the same shift underneath every play in this library. Raw AI chat is a good draft. AI chat connected to verified data is a working answer.

FAQ

  • At least 5. More reference accounts give the model a clearer pattern to match against.

     

     

  • The lookalike model matches on company profile, not size or brand recognition. If you want larger, more established accounts, add a company size filter to the prompt.

  • Yes. List your current customers in the prompt and Claude passes them through to Lusha as an exclusion.

  • No. A filtered search matches on criteria you set explicitly. Lookalike matching finds the pattern across your reference accounts and applies it, including matches you wouldn’t have thought to filter for.

     

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