Most inbound queues get worked in the order leads arrive, or by a generic lead score that treats every form fill the same. Neither approach knows which inbound lead actually resembles the contacts who became your best customers. Connect Lusha to Claude and this prompt checks a batch of inbound leads against your proven contact pattern, so the response queue is ordered by fit, not just by arrival time.
Prioritize inbound leads by lookalike fit
The prompt
Here are my highest-value customer contacts: [paste names or emails].
Here are today's inbound leads: [paste names or emails from your form
fills].
Using the Lusha connector, score each inbound lead against the pattern
from my best customer contacts - role, seniority, and company
profile. Return a table with lead name, match score, and matched
attributes.
Rank the full inbound batch from highest to lowest fit, and flag the
top five for an immediate response.
What you'll get back
The situation: a demand gen manager pastes 15 best-customer contacts and 18 inbound leads from the morning’s form fills, and asks for a ranked response order.
The output:
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 contact lists to see live results.
Why use Lusha in Claude
Every other lookalike play in this library is outbound: go find contacts who match a proven pattern. This one applies the same model to a pool of leads that already arrived, which changes what “prioritize” means — instead of ranking by a generic score or first-come order, the queue is ordered by how closely each lead actually resembles who became a customer before. The lead who filled out the form third gets worked first, if they’re the strongest match. Contact and company data is verified across multiple sources and handled under GDPR, CCPA, SOC 2 Type II, and ISO 27701 compliance.
FAQ
A generic lead score usually weighs firmographic fit and engagement generically. This scores specifically against the pattern from contacts who actually became customers, which can surface a strong-fit lead a generic score would rank lower.
Same underlying match logic, opposite direction. That play searches the market for new contacts to pursue. This one scores contacts you already have, from inbound, against the same pattern.
Same minimum as standard lookalikes: five reference contacts, though a larger, more consistent set produces a sharper pattern to score against.
Yes, via the API — this prompt shows the mechanic conversationally, but the same scoring logic can run automatically as leads come in, feeding a ranked queue instead of a manual batch.
The prompt matches business-profile attributes — role, seniority, company data — against contacts who submitted a form themselves. Lusha’s data is professionally sourced and opt-outs are honored automatically.
Ready to run this?
One data connection. Works in Claude, ChatGPT, your CRM, or any agent you build.
