# Connection Request Generator

Three connection requests under 300 characters, each with one specific reference, plus a recommendation on whether to send a note at all.

- Version 1.0, updated 18 September 2026
- Works with: Claude, ChatGPT, Gemini or any capable assistant
- Source: https://www.linkediz.com/prompts/connection-request

## Use when

- You have a researched prospect and a connection request to send.
- Your acceptance rate is below about 30% and you suspect the note.
- You are writing the note a template will fill for a batch of similar prospects.
- You are reaching out to someone senior where a pitch would end it immediately.

## Variables to replace

- `{{OBJECTIVE}}` — Objective. The single outcome this run should produce. One outcome, not three.
  Example: Twelve accepted connections a week from in-ICP finance directors
- `{{ROLE}}` — Your role. Your job title and what you are accountable for.
  Example: Founder, doing my own outbound until the first AE starts
- `{{COMPANY}}` — Your company. Name plus the one line you would use to introduce it.
  Example: Cadence — payroll reconciliation software for multi-entity finance teams
- `{{TONE}}` — Tone. How you actually write. Name a person or a publication if it helps.
  Example: Plain, short sentences, no exclamation marks, no "hope this finds you well"
- `{{PROSPECT_NAME}}` — Prospect name. As it appears on their profile.
  Example: Dana Whitfield
- `{{PROSPECT_ROLE}}` — Prospect job title. Their current title, verbatim.
  Example: Group Finance Director
- `{{PROSPECT_COMPANY}}` — Prospect company. Company name and size, if you have it.
  Example: Northbeam Logistics, ~900 staff, 5 countries
- `{{PROSPECT_PROFILE}}` — Profile and activity. Paste the About section, current role description, and anything they posted or commented on recently.
  Example: "12 years in finance ops, currently consolidating five ERPs into one." Posted last week about the pain of a five-week close after an acquisition.
- `{{OFFER}}` — The ask. What you want them to do next. Be specific about the size of the commitment.
  Example: A 20-minute call to see whether the multi-entity part applies to them

## How to use

1. Paste real profile text into {{PROSPECT_PROFILE}}. The evidence grade is only as good as what you give it.
2. Trust a "none" grade. A no-note request to a well-targeted person beats a generic note, and it does not burn the specific angle you might use later.
3. Check the character count yourself on the one you send — models miscount, and LinkedIn truncates without warning.
4. Keep the "after they accept" message. Most people win the connection and then send nothing for a week, which wastes it.

## Do not

- Putting the pitch in the note. The note is read in a list view next to fifteen others; a pitch there is a decline.
- Sending the same note to a batch by find-and-replacing the name. That is the pattern LinkedIn’s own acceptance-rate throttle is built to punish.
- Ignoring the 300-character limit because the draft "is nearly there". Truncation cuts mid-sentence.

## Context files this expects

- `OUTREACH.md` — https://www.linkediz.com/ai/files/outreach
- `BRAND-VOICE.md` — https://www.linkediz.com/ai/files/voice

## Where this sits

- Previous step: LinkedIn Prospect Research — https://www.linkediz.com/prompts/prospect-research
- Next step: Follow-up Sequence Builder — https://www.linkediz.com/prompts/follow-up-sequence

---

## The prompt

You are writing LinkedIn connection requests. You treat the 300-character note field as the hard constraint it is, and you know that a bad note performs worse than no note at all.

## Objective
{{OBJECTIVE}}

## Who I am
{{ROLE}} at {{COMPANY}}. Tone: {{TONE}}

## Who I am writing to
{{PROSPECT_NAME}}, {{PROSPECT_ROLE}} at {{PROSPECT_COMPANY}}
What I know about them, verbatim:
{{PROSPECT_PROFILE}}

## What I would eventually want
{{OFFER}}

## Hard rules
- The note field holds 300 characters including spaces. Anything longer is truncated by LinkedIn, and a truncated note is worse than none. Count the characters and print the count.
- Exactly one specific reference per note: something from their profile or activity that could not be true of anyone else. Two references reads as research rather than interest.
- No pitch, no meeting request, no link, no calendar. The note buys a connection, not a call.
- Do not open with "I came across your profile", "I hope this finds you well", "quick question", "I'd love to connect" or any sentence that would be identical for a different person.
- Do not compliment. "Impressive career" is filler and reads as automated.
- If I have given you nothing specific enough to reference, say so and recommend sending the request with no note. Do not manufacture a reference.

## Method
1. Find the one thing in the material that is genuinely specific.
2. Decide whether it supports a note at all. Grade the evidence: strong (they said it themselves, recently), weak (inferable from their role), none.
3. Write three variants:
   - Direct: names why I am reaching out.
   - Curious: asks about the specific thing, with no reason given.
   - Peer: positions us as two people with the same problem, no ask.
4. Recommend one, with the reason in one sentence.
5. Write the message to send AFTER they accept, which is where the actual conversation starts. Same rules, up to 600 characters, still no pitch.

## Output format

### Evidence grade
Strong / weak / none, and what it rests on.

### Recommendation
Which variant to send, or "send with no note", and why in one sentence.

### Variant A — direct
The note, then (n characters).

### Variant B — curious
The note, then (n characters).

### Variant C — peer
The note, then (n characters).

### After they accept
The follow-up message, under 600 characters, with the character count.

### What I would need to do better
The one piece of information that would have produced a stronger note.

---

## Notes

Written to a fixed structure and run through Claude and ChatGPT to confirm each one returns the output format it declares. That is not the same as a measured reply-rate benchmark, and nothing here claims one — if you run these at volume and have numbers, we want them.

---

Linkediz LinkedIn AI Toolkit — v1.0, 18 September 2026
Source and updates: https://www.linkediz.com/prompts/connection-request
LinkedIn plan limits and prices in this file: https://www.linkediz.com/linkedin-limits