// USE CASE
AI ICP Scoring for LinkedIn Leads | AtomSell
For teams sending to lists that are mostly the wrong people. On the usual stack every row costs enrichment credits before you know if it fits. Your agent drops obvious non-fits with free rules, scores the rest 1 to 10 with a reason and sends only to strong fits: 33% acceptance on 7,152 requests against 10 to 20% for unscored lists.
// Playbooks
5 playbooks
Enrich any LinkedIn profile with full structured data
LiveAnyone writing personalized outreach or scoring leads on more than a headline. Search results give you a name and a headline. Outreach built on a headline sounds generic, and copying profile fields by hand stops scaling after a dozen leads.
n8nsoonMCPRESTsoonMakesoonSales NavigatorICP scoring n8nCursorClayunder 2 seconds, against 1 to 5 minutes by hand Time per profileResearch any company in one prompt
LiveAEs, SDRs and RevOps who qualify accounts before outreach. A LinkedIn company page is mostly free-text About copy. You cannot filter, score or hand it to an AI as it is, so research stays manual: 3 to 5 minutes per account.
n8nsoonMCPRESTsoonMakesoonICP scoring LinkedInClayChatGPTunder 2 seconds, against 3 to 5 minutes by hand Time per companyScore LinkedIn and Sales Navigator leads by ICP before you write a word
LiveSDR leads, RevOps and founders who build lists in Sales Navigator. A Sales Navigator search returns hundreds of profiles and most of them are not a fit. Teams either message everyone and burn their daily sending capacity, or pay to enrich and score every row in a tool like Clay, including leads that will never qualify.
n8nsoonMCPRESTsoonMakesoonICP scoringSales Navigator ClaudeCursorLinkedIn7,152 Connection requests sentTurn a trade fair exhibitor list into booked meetings
LiveSales and partnership teams who go to trade fairs and want their calendar full before they land. A big fair publishes thousands of exhibitors. Nobody reads a catalog of 4,000 companies, so teams pick a few famous names, write the same message to everyone and hope to catch the rest at the booth. On a usual stack every ICP track and every sender is a separate fixed campaign: seven tracks and two senders make 14 campaigns in HeyReach, and every row is enriched and classified with Clay credits, including the companies that never qualify.
n8nsoonMCPRESTsoonMakesoonEvent outreachICP scoring Sales NavigatorChatGPTLinkedIn20 Meetings booked in one month before a medtech fairTurn LinkedIn post likers and commenters into qualified leads
LiveFounders, GTM engineers and outbound agencies who want warm leads instead of cold lists. People who like and comment on posts in your niche are raising their hand: the topic is on their mind this week and they will recognize what you talk about. But the signal is scattered across hundreds of posts, and working it by hand means opening every post, scrolling every reaction and reading every profile. So most teams go back to bought lists that accept 10 to 20% of requests.
n8nsoonMCPRESTsoonMakesoonPost engagersICP scoring ChatGPTCursorLinkedIn2,499 Connection requests sent
// Get started
Start building with AtomSell
Create an account, get an API key, and run any playbook end-to-end.
Create your account