Sales & Outreach

Verified against ChatGPT · 2026-08-06

Write a LinkedIn outreach message that earns a reply before you ever pitch

Builds a two-touch LinkedIn sequence — a connection note under the platform's 300-character limit and a value-first follow-up sent after acceptance — anchored to a specific profile signal instead of a recycled connection request.

ChatGPTClaudeLinkedIn Sales Navigator7 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

I want to reach out to Anjali Rao, Head of Revenue Operations at Wayfinder Analytics, on LinkedIn. Here's what's actually on their profile or recent activity: commented on a post about RevOps teams drowning in disconnected spreadsheets. What we do: a RevOps reporting platform that unifies pipeline data across tools. The reason I think this is relevant to them specifically: her comment specifically named the spreadsheet-reconciliation problem we solve. My own relevant background or reason for reaching out: we both spoke at the same regional RevOps meetup last spring.

Write two messages, built to be sent days apart, not back to back.

1. CONNECTION NOTE — hard cap 300 characters, LinkedIn's platform limit for connection request notes, referencing commented on a post about RevOps teams drowning in disconnected spreadsheets specifically, with zero pitch anywhere in it. This message has exactly one job: be worth accepting. If you cannot reference commented on a post about RevOps teams drowning in disconnected spreadsheets specifically within the character limit without cutting it down to something generic, say so rather than quietly writing a note that only technically mentions it.

2. FIRST MESSAGE AFTER THEY ACCEPT — written as a separate follow-up sent after the connection is accepted, not immediately, and never in the same breath as the connection request itself. Lead with something genuinely useful, interesting, or specific tied to her comment specifically named the spreadsheet-reconciliation problem we solve — an observation, a question, a resource — before any mention of a RevOps reporting platform that unifies pipeline data across tools. If we both spoke at the same regional RevOps meetup last spring gives a real reason for the outreach beyond selling something, use it here; a rep with a genuine shared context has more room to be direct than one with none. If you cannot avoid the message feeling like a pitch given what's actually available, say so explicitly instead of forcing one in just to satisfy the structure.

TONE
Write both messages like a peer who did their homework, not a rep working a list. Ban "I came across your profile and was impressed by your experience" and any close variant of it — that exact phrase, or something functionally identical to it, appears in more automated LinkedIn outreach than any other single line, and it signals templated outreach within the first few words regardless of how personalized the rest of the message is. Ban exclamation points in both messages; enthusiasm punctuation reads as sales voice on a platform where the best-performing outreach reads like it was typed by a person, not scheduled by a sequence tool.

LENGTH
Connection note: one to two sentences, hard character cap as stated. Follow-up message: no more than four sentences, since a long first message after connecting reads as presumptuous before any real rapport exists.

CLOSING HONESTY CHECK
After both messages, state plainly whether commented on a post about RevOps teams drowning in disconnected spreadsheets is specific enough to justify the personalization used, or generic enough that a reader would recognize this as a templated message with a name swapped in — a signal like "works in your industry" or "has an impressive career" should be flagged as too weak to carry either message, even if the messages themselves read smoothly.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

LinkedIn actually enforces a 300-character limit on connection request notes at the platform level, so writing to that constraint from the first draft avoids producing a note that reads well in isolation and then gets silently truncated mid-sentence the moment it's actually sent — a failure a rep often doesn't notice until a prospect replies confused about a sentence that never finished. Splitting the outreach into two touches instead of pitching inside the connection request itself reflects a real, widely observed behavior pattern on the platform: a connection note that asks for something beyond the connection itself measurably lowers accept rates, because it reframes an easy, low-stakes yes into a request with strings attached before any relationship exists to justify the ask. Explicitly banning "I came across your profile and was impressed by your experience" targets the single most recognizable line in automated LinkedIn outreach — it has become a tell in the same way "Dear Sir or Madam" is a tell for a mass mailing, and a model left to write generic personalization gravitates toward it by default because it technically applies to any profile without requiring any actual reading of it. The instruction to use sender_context when a genuine shared connection exists — a shared event, a mutual contact, overlapping work — matters because that kind of context licenses a level of directness that pure profile-based personalization cannot; conflating the two produces messages that either overclaim a relationship that doesn't exist or underuse one that does. The closing honesty check exists because profile-based personalization is uniquely easy to fake convincingly: a model can write two fluent, specific-sounding messages around a signal that is actually generic — "has an impressive career," "works in tech" — and the fluency of the writing gives no signal at all about whether the underlying anchor could support it, which is exactly the gap a rep needs flagged before hitting send on a message that will read as templated to the one person best positioned to notice.

What you get back

Connection note (187 characters): "Anjali — your comment about RevOps teams drowning in spreadsheet reconciliation hit close to home, that's the exact problem we spend our days on. Would love to connect."

Verified against

ChatGPT GPT-5.1 · 2026-08-06

Claude Sonnet 4.5 · 2026-08-06

Changelog

  • 2026-08-06 Initial publish, verified against ChatGPT (GPT-5.1) and Claude (Sonnet 4.5).

Need this built into your business?

If a prompt isn't enough — Google Ads management, built and maintained for you — that's Scult's day job.

EXPLORE GOOGLE ADS MANAGEMENT
All Sales & Outreach prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY