Warm Up a LinkedIn Prospect by Engaging Where They Already Are

# Be where they are — Loadout

```yaml
loadout: be-where-they-are
tier: apex                # Apex tier (or an active Apex trial)
mcp: https://apex.leadshark.io/mcp
```

**The job:** The sharpest read on a prospect is what they engage with. See who they comment on and what they react to, then show up in those rooms — before any DM.

## 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. **Who is the prospect (or shortlist) to warm up?**
2. **What can you genuinely add to their conversations?** (your expertise/angle)
3. **Any topics or people to stay away from?**

## Steps

1. **See** — call `get_person_activity`: See the prospect's recent comments and reactions — the rooms they're already in.
2. **Decide**: Pick the 2–3 conversations where a comment from you is genuinely additive.
3. **Act** — call `comment_on_post`: Comment with substance where they're active; react where a comment would be noise.
4. **Act** — call `send_connection_request`: Connect once you're familiar — referencing the shared thread.

## 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

Comments are paced within your daily budget and drafted for approval, so the warm-up reads as a human being present — because you approved every word.

Using Apex: for {prospect}, pull their recent LinkedIn activity — who they comment on and what they react to. Pick the 3 conversations where I can add something real, draft a substantive comment for each (no generic praise), and queue them. After two land, draft a connection note referencing the shared thread. Everything through the approval queue.