Start from Lusha in ChatGPT or type @Lusha before sending.
@Lusha Build an AI-recommended lookalike buyer list
based on my best buyer contacts.
SEED BUYERS:
Add 5-100 buyer contacts who represent strong-fit buyers,
champions, customers, expansion contacts, or high-quality
opportunities.
You can use LinkedIn URLs, business emails, Lusha contact IDs,
or name + company details.
1. [LinkedIn URL / email / name + company / Lusha contact ID]
2. [LinkedIn URL / email / name + company / Lusha contact ID]
3. [LinkedIn URL / email / name + company / Lusha contact ID]
4. [LinkedIn URL / email / name + company / Lusha contact ID]
5. [LinkedIn URL / email / name + company / Lusha contact ID]
BEST BUYER CONTEXT:
Why these buyers are good examples:
[champions / decision-makers / high ACV / fast sales cycle /
strong expansion / active product users / high intent /
strategic segment / other]
ICP:
Best-fit titles: [titles]
Best-fit departments: [Sales / Marketing / RevOps / IT /
Operations / Customer Success / Finance / HR / other]
Best-fit seniority: [manager / director / VP / C-level]
Best-fit industries: [industries]
Best-fit company size: [employee range]
Best-fit regions: [regions]
EXCLUDE:
Do not include:
- Existing customers: [company domains or contacts, if any]
- Competitors: [company domains, if any]
- Open opportunities: [company domains or contacts, if any]
- Poor-fit segments: [titles, departments, industries,
regions, company sizes, or business models to exclude]
MY PRODUCT:
[One sentence describing what you sell and the problem
it solves]
Using Lusha, do the following:
1. VALIDATE THE SEED BUYERS
Confirm that each seed buyer can be matched to a real
Lusha contact profile.
Return:
- Name
- Current title
- Current company
- Department
- Seniority
- Location
- Match status
If fewer than 5 seed buyers can be verified, ask me
for more seeds before running the lookalike search.
2. FIND LOOKALIKE BUYERS
Use the verified seed buyers to find similar contacts.
Prioritize contacts that appear similar across:
- Title
- Department
- Seniority
- Company type
- Industry
- Company size
- Region
- ICP relevance
Do not include contacts or companies listed in the
exclusion section.
3. VERIFY EACH LOOKALIKE CONTACT
For each lookalike buyer, return:
- Name
- Current title
- Current company
- Department
- Seniority
- Location
- LinkedIn profile if available
- Whether the person appears to still be at the company
4. ENRICH CONTACT DATA
For each lookalike buyer, return:
- Verified business email availability
- Direct or mobile phone availability
- DNC status if available
- Last updated date if available
If contact data is not available or cannot be revealed,
say so clearly rather than guessing.
5. ENRICH EACH COMPANY
For each lookalike buyer’s company, return:
- Company name
- Domain
- Industry
- Employee count
- HQ location
- Revenue range if available
- Company LinkedIn if available
6. CHECK RECENT SIGNALS
For each lookalike buyer or their company, check recent
signals from the last 6 months, if available.
Prioritize:
- Promotion
- Company change
- 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
- Intent topics related to my product, if available
7. CREATE AN EXPLAINABLE RECOMMENDATION SCORE
Create a recommendation score from 1-100 using only
the Lusha data returned and the ICP context I provided.
Break the score into:
- Buyer match: 35 points
How similar the contact appears to the seed buyers.
- ICP fit: 30 points
How well the contact and company match my target market.
- Timing: 20 points
Whether recent contact or company signals make outreach
more timely.
- Actionability: 15 points
Whether verified contact data is available and usable.
Make the score explainable. Do not present it as a
prediction that the buyer will convert or purchase.
If there is not enough verified data to support a score,
mark the score as low-confidence and explain what is missing.
8. ASSIGN A RECOMMENDATION
Assign one recommendation:
Contact now:
Strong buyer match + high ICP fit + relevant signal
or strong actionability.
Add to campaign:
Strong buyer match + good ICP fit, but weaker timing.
Nurture:
Partial fit, weak signal, or unclear urgency.
Review:
Interesting match, but missing data or unclear fit.
Exclude:
Poor fit, disqualified, competitor, existing customer,
open opportunity, or unverifiable contact.
9. CREATE AI RECOMMENDATIONS
For each Contact now buyer, write:
- Why this person looks like our best buyers
- Why now may be a good time to reach out, if supported
by signals
- What angle to lead with
- One subject line under 7 words
- One opening line under 30 words
- One discovery question
Do not:
Invent signals, titles, responsibilities, tools, vendors,
internal projects, contract status, or buying intent.
Claim the buyer is ready to buy.
Present the score as a conversion prediction.
Include excluded contacts or companies.
Force personalization when the data is weak.
10. OUTPUT FORMAT
Return:
- Seed buyer validation
- Lookalike buyer table
- Contact verification
- Contact data availability
- Company enrichment
- Recent signals, if any
- Explainable recommendation score with breakdown
- Confidence level
- Recommendation
- Recommended outreach angle
- Excluded contacts and why
Do not invent contacts, companies, emails, phone numbers,
signals, scores, or recommendations. If Lusha cannot verify
a contact, company, or signal, mark it clearly.
