// Playbook
LiveLinkedIn Post Engagers to Leads: AI Playbook | AtomSell
// When to use
Problem
Founders, 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.
// What you get
Outcome
- Finds fresh posts on the topics your buyers care about
- Pulls everyone who reacted or commented into a data table
- Drops obvious non-fits (students, recruiters, job seekers, vendors) before any AI call
- Scores the rest against your ICP
- Writes a connection note for the best fits, built from their role and what they commented
- Sends the requests and keeps every reply in one inbox
// Results
Proof
// Building blocks
AtomSell Actions used
Search posts
Find posts by keywords and date, by author, from your network, or mentioning a person or company. Ask your agent: "Find posts from the past week about AI SDRs."
Get post reactions
List everyone who reacted to a post, with the reaction type. Ask your agent: "Pull everyone who liked these 3 posts into a table."
Get post comments
List every comment on a post with author and text. Ask your agent: "Who commented on this post and what did they say?"
Create a table
Create a data table with typed columns and a key that prevents duplicates. Ask your agent: "Create a table called Event leads."
Write table rows
Add or update up to 1,000 rows at once. Ask your agent: "Save the scores and reasons to the table."
Enrich a profile
Open a full profile: experience, education, skills, languages, certifications, summary, contact details where visible, and how they relate to you. Ask your agent: "Open the full profiles of the top 5 and tell me why each fits."
Send a connection request
Send a connection request with a personal note of up to 300 characters. Ask your agent: "Send the notes to the top 10."
List lead conversations
List saved conversations with your leads across all profiles, each classified from the latest reply. Ask your agent: "Show everyone who replied this week, warmest first."
// How it works
Flow
// Run it
Implementations
Connect AtomSell to Claude (Settings, Connectors, Add custom connector, https://app.atomsell.ai/mcp), connect your LinkedIn profile in AtomSell, then paste the prompt into a new chat. Start your 3-day free trial at app.atomsell.ai/register.
Prompt
Run this end to end without asking me anything. If you need to choose, pick the fastest option and tell me which. 1) Find posts from the past week about "[TOPIC 1]" or "[TOPIC 2]" with 20 to 300 reactions, first page of results only, skip hiring posts, pick the best 2. 2) Pull the first page of reactions and comments on those 2 posts and save everyone to a table called "Post engagers". 3) Score each person 1 to 10 from their headline against this ICP: [YOUR ICP]. Skip students, recruiters and job seekers. 4) Open the full profiles of the top 3 only and confirm the fit. 5) Show a short table: first name, last initial, headline, score. 6) Write a connection note under 200 characters for each of the top 3, built from their role and what they wrote or liked. Sound like a person, no pitch, no product name, no dashes.
Then
Send these connection requests now and show their status.
Example output fields
linkedin_url, first_name, last_name, headline, source (reaction or comment), post_url, score, connection_note, status
// Connects with
Integrations used
// Fits into
Use cases
// Questions
FAQ
- Can I search by topic instead of one post URL?
- Yes. The agent searches posts by keyword, author or date and picks the ones with real engagement.
- Are commenters better leads than likers?
- Commenters usually show stronger intent, and their comment gives you the best opening line. The playbook pulls both and lets the score decide.
- Is it safe for my account?
- AtomSell is built on know-how from 5.2M+ sales actions with zero accounts lost. The engine paces every action, so the agent cannot exceed safe limits.
- Do I need Sales Navigator?
- No. Post search, reactions and comments work on any LinkedIn account.
// Explore more
Related playbooks
Find who is going to an event and book meetings before it starts
Founders and sales teams travelling to conferences, meetups and trade shows. People announce on LinkedIn that they are going to an event, but a search by event name returns sponsors, organizers and media too. By the time a list is built by hand, the event is over.
Score LinkedIn and Sales Navigator leads by ICP before you write a word
SDR 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.
Investor outreach on LinkedIn: write from what each partner posted today, not from a template
For founders raising a pre-seed or seed round. You need meetings with the right partner at a few hundred funds, every partner has a different thesis, and the best reason to write, what they posted or commented this week and the deals their fund just announced, changes every day. On the usual stack that means a fund list exported from a database weeks ago, a spreadsheet for status, a sequencer that sends every investor the same cadence, and an hour of manual LinkedIn reading every morning. Personalization stops at a first-name variable. Two co-founders write to the same fund, a decline in one inbox never reaches the other, and the thread between LinkedIn and email gets lost.
// Get started
Start building with AtomSell Actions
Create an account, get an API key, and run this playbook end-to-end.
Create your account