Follow Up and Close Your Captured LinkedIn Leads with an AI Agent

# Closer — Loadout

```yaml
loadout: closer
tier: apex                # Apex tier (or an active Apex trial)
mcp: https://apex.leadshark.io/mcp
```

**The job:** Your magnet captured their email — now finish the job. Closer pulls the people who opted in, reads what you've already said and whether they opened what you sent, then drafts a personal follow-up to move them to the next step. You stay in the loop on every one: nothing — no DM, no email — is sent without your approval. Create makes demand, capture raises the hand — Closer closes it.

## 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 lead-magnet page's leads should I work?**
2. **What's the next step you want them to take?** (book a call, reply, buy — the close)
3. **Daily follow-up cap, and anyone off-limits?** (existing customers, do-not-engage)

## Steps

1. **See** — call `get_page_leads`: Pull the hand-raisers — everyone who opted into your lead magnet, with the email they gave and what they came for.
2. **Decide** — call `get_lead_activity`: Read the relationship: did they open what you sent, have you talked before, anyone flagged do-not-engage — so you follow up from context, never cold.
3. **Decide** — call `get_messages_with_person`: Pull the existing thread and pick up exactly where it left off, instead of restarting the conversation.
4. **Act** — call `send_message`: Close the ones you're connected to with a personal follow-up referencing what they downloaded and the last thing said — approval-gated.
5. **Act** — call `send_email`: For email-only leads, send one personal note via Apex — same approval gate, logged.

## 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

Human-in-the-loop by design: Closer drafts, you send — it never messages anyone on its own. Warm by definition — these people raised their hand — and Closer still reads the full history before it writes (get_lead_activity, get_messages_with_person), so no one gets a cold-sounding 'just following up.' Customers and do-not-engage are skipped, follow-ups are paced inside your daily caps, and every message — DM or email — waits in the approval queue and is logged.

Using Apex, pull the leads captured by {lead magnet / page}. For each, check get_lead_activity — did they open what I sent, have we talked, anyone I shouldn't touch — and read our existing thread with get_messages_with_person so I pick up where we left off. Draft a personal follow-up that references what they downloaded and moves them toward {next step}: a LinkedIn DM if we're connected, a short email via Apex if not. Respect my daily caps, skip customers and do-not-engage, and queue every message for my approval.