Find lookalike accounts from your best customers in ChatGPT

Built by: Lusha
Time to build: 1 min
Difficulty: Easy
Tools: ChatGPT ▪ Lusha
Type: Prompt

Example outputs in this play are illustrative — they reflect the structure, fields, and format of real Lusha connector output, but were not pulled from a live session. Run the prompt with your own customer list to see live results.

Your best customers already tell you what good-fit accounts look like. Same market. Similar size. Similar business model. Similar operational pressure. Similar reasons to buy.

The problem is that most teams turn that knowledge into vague ICP language: “mid-market SaaS companies,” “fast-growing teams,” “RevOps-led organizations.” That helps, but it does not give sales a concrete list of who to target next.

This prompt uses Lusha in ChatGPT to find companies similar to your best customers, enrich each lookalike account, and prioritize the strongest matches. Instead of starting with broad filters, you start with real customer examples and let Lusha help you find more accounts that look like them.

How to start

Open in Claude Open in ChatGPT
1

Open Lusha in ChatGPT

Go to Lusha in ChatGPT and click “Start chat.” Every conversation started this way is automatically Lusha-enabled.

2

Or invoke Lusha in any existing conversation

Type @Lusha in the prompt bar and select Lusha from the dropdown. Unlike Claude, Lusha does not activate automatically in every ChatGPT conversation. You must invoke it every time.

3

Paste your best customer list and send

Copy the prompt below, add at least five seed customer domains, include any exclusions, and send. Lusha finds lookalike companies and helps you prioritize the best accounts to target next.

The prompt

Start from Lusha in ChatGPT or type @Lusha before sending.

@Lusha Find lookalike accounts based on my best customers.

SEED CUSTOMERS:
Add at least 5 customer company domains or LinkedIn
company URLs:
1. [customer domain or LinkedIn company URL]
2. [customer domain or LinkedIn company URL]
3. [customer domain or LinkedIn company URL]
4. [customer domain or LinkedIn company URL]
5. [customer domain or LinkedIn company URL]

EXCLUDE:
Companies we should not include:
- Existing customers: [company domains, if any]
- Competitors: [company domains, if any]
- Poor-fit segments: [industries, regions, or sizes to exclude]

ICP CONTEXT:
Best-fit industries: [industries]
Best-fit company size: [employee range]
Best-fit regions: [regions]
Target personas: [personas]
My product: [one sentence describing what you sell and
the problem it solves]

Using Lusha, do the following:

1. FIND LOOKALIKE COMPANIES
   Use the seed customers to find companies that look
   similar to our best customers.

   Only use the seed companies I provided.
   If I provide fewer than 5 seeds, ask me for more
   before running the lookalike search.

2. ENRICH EACH LOOKALIKE ACCOUNT
   For each lookalike company, return:
   - Company name
   - Domain
   - Industry
   - Employee count
   - HQ location
   - Revenue range if available
   - Company LinkedIn if available

3. CHECK ICP FIT
   Compare each lookalike account against the ICP context.

   Score each account:
   - High fit
   - Medium fit
   - Low fit
   - Exclude

   Base the score on industry, company size, region,
   and relevance to my product.

4. CHECK RECENT BUYING SIGNALS
   For high-fit and medium-fit accounts, check for recent
   company signals from the last 6 months.

   Prioritize:
   - Hiring surges
   - Hiring surges by relevant department
   - Hiring surges by location
   - Headcount increases or decreases
   - IT spend changes
   - Website traffic changes
   - Commercial activity news
   - Corporate strategy news
   - Financial events news
   - People news
   - Product activity news
   - Risk news

5. PRIORITIZE ACCOUNTS
   Rank the lookalike accounts:

   Tier 1:
   Strong lookalike match + high ICP fit +
   recent relevant signal

   Tier 2:
   Strong lookalike match + high ICP fit,
   but weak or no recent signal

   Tier 3:
   Medium fit or unclear urgency

   Exclude:
   Poor fit, disqualified, competitor, existing customer,
   or unclear match

6. FIND STARTING CONTACTS
   For each Tier 1 account, find one relevant contact
   matching the target persona.

   Return:
   - Name
   - Current title
   - Department
   - Seniority
   - Location
   - LinkedIn profile if available
   - Verified business email availability
   - Direct or mobile phone availability
   - DNC status if available

7. CREATE THE OUTREACH ANGLE
   For each Tier 1 account, write:
   - One reason this account looks like our best customers
   - One signal-based reason to reach out now, if available
   - One suggested opening line under 30 words

8. OUTPUT FORMAT
   Return:
   - Lookalike account table
   - ICP fit score
   - Strongest recent signal
   - Priority tier
   - Starting contact for Tier 1 accounts
   - Suggested outreach angle
   - Accounts excluded and why

Do not invent companies, contacts, emails, phone numbers,
or signals. If Lusha cannot verify a company or contact,
mark it clearly.

What you’ll get back

 

A prioritized list of lookalike accounts, enriched with company data, recent signals, and starting contacts for the best-fit companies. Here’s what the output looks like:

Lookalike accounts — Lusha

FieldValue
Seed customers5 customer domains used as lookalike seeds
Lookalikes found25 companies · 9 high-fit accounts · 4 Tier 1 accounts
Best-fit account[Company A] · B2B SaaS · 500–1,000 employees · North America
Strongest signalHiring surge in Sales · detected in the last 30 days
Starting contactR.M. · VP Sales · verified email available · mobile available
Outreach angleLooks like your best customers and shows current Sales team growth

Example outputs in this play are illustrative — they reflect the structure, fields, and format of real Lusha connector output, but were not pulled from a live session. Run the prompt with your own customer list to see live results.

 

Why use Lusha in ChatGPT to find lookalike accounts

 

A strong ICP is useful, but your best customers are often even more useful. They show what a real good-fit account looks like after the deal is closed, the product is adopted, and the value is proven.

Lusha helps turn those customer examples into a new target account list. Instead of starting with broad filters, the prompt starts with seed companies and finds similar accounts. Then it enriches the results, checks fit, looks for recent signals, and helps prioritize which accounts are worth acting on first.

The signal layer matters because similarity alone is not urgency. A company may look like your best customers but still have no clear reason to buy now. A lookalike account with a recent hiring surge, IT spend increase, leadership change, or commercial activity signal is more useful because it gives the rep both fit and timing.

The result is not just “more accounts.” It is a cleaner way to expand from what already works.

Lusha data is sourced and used in accordance with Lusha’s Privacy Policy and Terms of Use. Lusha is GDPR compliant and covers contacts across North America, EMEA, and APAC.

FAQ

  • How many seed customers do I need?

    Use at least five seed customers. The better the seed list, the better the lookalike output. Choose customers that represent strong fit, strong retention, high ACV, fast adoption, or a use case you want to repeat.

  • Should I use domains or company names?

    Domains are best because they make the company match more precise. You can also use LinkedIn company URLs. If you only have company names, verify them before using the list as lookalike seeds.

  • Can I exclude existing customers?

    Yes. Add existing customer domains, competitors, or poor-fit segments in the exclude section. The prompt asks Lusha to avoid accounts that should not be included in the final target list.

  • What makes a lookalike account worth contacting now?

    The strongest accounts combine fit and timing. A company that looks like your best customers is a good starting point. A company that also shows a recent buying signal, such as hiring growth, IT spend change, or relevant company news, is more urgent.

  • Can I use this for ABM planning?

    Yes. This prompt is useful for building ABM account lists because it starts from real customer examples, enriches the lookalike companies, and prioritizes accounts by fit, signal, and next action.

Related Prompts

Ready to run this?

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

Get free access Read the Docs