02 · CaptureApex tier
Competitor-post capture
Turn a Competitor's LinkedIn Post into a Warm Lead List with an AI Agent
Their audience is your audience. Pull everyone who engaged with a competitor's post, qualify them, and reach out with the context of what they just engaged with.
The Loadout, step by step
- See
list_post_engagersPull every commenter and reactor from the competitor's post. - Decide
enrichEnrich each engager; keep only ICP fits. - Decide
enrich_companyCheck the accounts behind the best fits. - Act
send_connection_requestConnect with a note referencing the post they engaged with — approval-gated.
The loadout.md — paste it to your agent
One portable file: config questions first, real MCP tools in the steps, a hard approval gate. Save it as competitor-post-capture.loadout.md or paste it straight into Claude, ChatGPT, or Cursor once Apex is connected.
# Competitor-post capture — Loadout ```yaml loadout: competitor-post-capture tier: apex # Apex tier (or an active Apex trial) mcp: https://apex.leadshark.io/mcp ``` **The job:** Their audience is your audience. Pull everyone who engaged with a competitor's post, qualify them, and reach out with the context of what they just engaged with. ## Before you run — ask the user Only ask what you don't already know — check the conversation, your memory, and the account itself first. Confirm anything you inferred in one line instead of re-interviewing. 1. **Which competitor or creator's audience are you capturing?** 2. **What filter makes someone worth contacting?** (title, company size, region) 3. **What's the note angle — how do you reference what they engaged with?** ## Steps 1. **See** — call `list_post_engagers`: Pull every commenter and reactor from the competitor's post. 2. **Decide** — call `enrich`: Enrich each engager; keep only ICP fits. 3. **Decide** — call `enrich_company`: Check the accounts behind the best fits. 4. **Act** — call `send_connection_request`: Connect with a note referencing the post they engaged with — approval-gated. ## STOP — approval gate Present everything you found and drafted BEFORE any write. Do not send, schedule, publish, connect, or create automations until the user approves. Edits beat re-drafts: apply their changes, don't start over. ## Never - Write to LinkedIn without explicit approval this run. - Invent facts, numbers, results, or people. - Contact anyone on the do-not-engage list, or double-touch someone (check `list_actions` first). - Retry around a refusal — report what was refused and why. ## Done means - The user approved the drafts (aim for ≤2 edit rounds). - Approved actions are queued or scheduled — verify via `list_actions`. - Report back: what ran, what's staged, and where to monitor it. ## Why this stays account-safe Reads are unlimited; the writes (connects) are paced, capped, deduped against people you've already touched (list_actions), and queued for your approval.
In a hurry? The one-liner
Using Apex, pull everyone who commented on {competitor}'s last 3 posts. Enrich each for title and company, keep only VP+ at 50–500-employee B2B SaaS, and draft a personalized connection note referencing their comment. Put every request in the approval queue — send nothing until I confirm.Run this Loadout with your agent
Connect Claude, ChatGPT, or Cursor to Apex in about five minutes — one-time 24-hour free trial, no credit card.