# LinkedIn Outreach Personalizer A first message and its follow-up, built from a stated hypothesis, with every claim traceable to something you actually gave it. - Version 1.0, updated 18 September 2026 - Works with: Claude, ChatGPT, Gemini or any capable assistant - Source: https://www.linkediz.com/prompts/cold-outreach-personalizer ## Use when - You have research on a prospect and need the message that follows it. - Your messages get read and not replied to. - You are writing the first touch for a sequence and need it to be the strong one. - You want to give an agent an instruction it can run per prospect without supervision. ## 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 - `{{PRODUCT}}` — What you sell. The thing, the outcome it produces, and who signs for it. Example: A reconciliation layer that closes multi-entity payroll in two days instead of nine. Bought by the Finance Director, used by the payroll manager. - `{{PROOF}}` — Proof you can cite. Named customers, numbers you are allowed to publish, or "none yet" — which is a valid answer. Example: Two logistics customers of similar size. One cut close from nine days to three. Named reference available under NDA; numbers publishable without the name. - `{{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" - `{{CONSTRAINTS}}` — Constraints. Word limits, banned words, compliance rules, anything that makes an otherwise good answer unusable. Example: Connection notes under 280 characters. No "quick question", no "circling back". Legal forbids naming customers without written consent. - `{{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. Run the Prospect Research prompt first and paste its value hypothesis into {{PROSPECT_PROFILE}} along with the raw profile text. 2. Fill {{PROOF}} honestly, including "none yet". A model with no proof writes a more honest message than one that invents a case study. 3. Read "Why each line is there". After five runs you will stop needing the prompt for straightforward prospects, which is the correct outcome. 4. Send the follow-up. About half the replies to a well-aimed first message arrive after the second one. ## Do not - Adding a second reference "to show you did the work". Two references reads as a dossier and changes the tone from interested to transactional. - Putting a calendar link in the first message. It converts a conversation into a funnel step before they have agreed there is anything to discuss. - Keeping a hypothesis the model rated low confidence. That is the message that gets the "who is this?" reply. ## Context files this expects - `OUTREACH.md` — https://www.linkediz.com/ai/files/outreach - `BRAND-VOICE.md` — https://www.linkediz.com/ai/files/voice - `PRODUCT.md` — https://www.linkediz.com/ai/files/product - `OBJECTIONS.md` — https://www.linkediz.com/ai/files/objections ## 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 a first LinkedIn message from one working person to another. You are not writing marketing copy. The test for every sentence: would a busy person read it and think "this is about me", or "this is about them"? ## Objective {{OBJECTIVE}} ## Me {{ROLE}} at {{COMPANY}} What we do: {{PRODUCT}} Proof I may cite: {{PROOF}} Tone: {{TONE}} Constraints: {{CONSTRAINTS}} ## Them {{PROSPECT_NAME}} — {{PROSPECT_ROLE}} at {{PROSPECT_COMPANY}} {{PROSPECT_PROFILE}} ## The ask {{OFFER}} ## Method 1. State the hypothesis first, before writing anything: one sentence about what is probably true for this person that makes my product relevant. If the evidence does not support one, say so and stop — a message with no hypothesis is a template and should be sent as one, not dressed up. 2. Choose the single reference. It must be checkable by the recipient and specific to them. 3. Write the message in this shape: - Line 1: the reference. No greeting beyond their first name. - Line 2: the hypothesis, stated as something you have observed elsewhere, not as a claim about them. "The pattern I keep seeing is X" invites correction; "You clearly have problem X" invites a defence. - Line 3: the question. Answerable in one line, genuinely open, and useful to me whichever way they answer. 4. The ask goes in the follow-up, not here — unless my stated objective is explicitly a meeting request, in which case put it in one short final line. 5. Write the follow-up for five business days later. It must ADD something: a number, a counter-example, a link to something useful that is not mine. Never "just bumping this". 6. Self-check before returning: remove every sentence that would be true of a different prospect. ## Hard rules - Under 700 characters for the message body. Print the character count. - One reference. One hypothesis. One question. - No compliments, no "I hope you don't mind me reaching out", no "we help companies like yours", no three-adjective descriptions of my product. - Never state a fact about their company that I did not give you. If you want one, ask me for it in the "what would make this better" section. - If they are the wrong person, say so instead of writing the message. ## Output format ### Hypothesis One sentence, plus the evidence and a confidence rating. ### Message The message. Then (n characters). ### Why each line is there One line per line of the message. This is how I learn to write the next one myself. ### Follow-up, day 5 The message. Then (n characters). ### What I would cut if it has to be shorter The specific sentence and what is lost. ### What would make this better The one piece of information you did not have. --- ## 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/cold-outreach-personalizer LinkedIn plan limits and prices in this file: https://www.linkediz.com/linkedin-limits