LeadHaste

Cold Email Writing prompts

Paste-ready prompts that write, critique, and sharpen cold emails that actually get replies — no fill-in-the-blank templates.

85 prompts · paste-ready, no variables to fill · free

These prompts cover the entire cold email craft: first lines and subject lines, full emails written from scratch, signal-triggered emails built from job postings, funding news, and tech-stack data, plus the unglamorous work that decides whether anything lands — spam-word scrubs, ruthless critiques, and A/B variants. Every prompt interviews you before it writes, so you never fill in a template variable or get generic output.

They're built for SDRs, founders, and sales leaders who send real volume through tools like Smartlead, Instantly, and Clay. To get the most from them, answer the interview questions with specifics — real numbers, real customer outcomes, real prospect data. The model can only be as sharp as what you feed it, and these prompts are designed to force the right inputs out of you.

LinkedIn & Social SellingIntermediate

Build a 3-touch LinkedIn DM sequence that escalates without annoying

Designs a complete 3-touch DM sequence where each message earns its place: a trigger-based opener, a value-led middle touch that isn't a bump, and a graceful close with no guilt-trip. Includes the psychology behind each touch and adapts wording to manual sending or tools like HeyReach.

Any LLMGet prompt →
Follow-Ups & SequencesBeginner

Build a complete 4-touch cold email sequence from scratch

Generates a launch-ready 4-touch sequence where each email plays a defined role — opener, proof, angle shift, close — with word caps, subject lines, and send delays included. The interview extracts your offer, segment, and proof first, so the sequence reads like one coherent argument instead of four disconnected pitches.

Any LLMGet prompt →
Automation & Workflow DesignAdvanced

Build a system prompt for an AI cold email reply agent

Interviews you about your offer, booking flow, and voice, then generates a complete production system prompt for an AI reply agent — classification taxonomy, response rules, escalation conditions, and a strict JSON output contract an n8n or Zapier workflow can parse. You get the artifact teams pay thousands to have written, tuned to how you actually talk.

Claude, ChatGPT, GeminiGet prompt →
Personalization at Scale (Clay & Claygents)Advanced

Generate a cold email first line from scraped research data

The workhorse of AI-personalized outbound: converts whatever research your enrichment waterfall produced into one 12–22-word observation-led first line per row. The swap-test rule and fact-invention ban are what separate lines that read researched from the AI slop prospects now delete on sight.

Any LLMGet prompt →
Sales Copywriting & AssetsBeginner

Generate an outcome-first value proposition buyers can repeat

Builds a complete value proposition system — primary line, three angle variations, a disqualifier, and channel-ready versions — instead of one throwaway tagline. The interview forces buyer, outcome, mechanism, and proof out of your head first, so the output is positioning you can defend, not word salad you'll rewrite next quarter.

Any LLMGet prompt →
Cold Email WritingBeginner

Get your cold email critiqued and scored like a skeptical prospect

Runs your cold email through a three-pass review: a brutal line-by-line read from a busy prospect's perspective, a five-dimension strategic score, and a rewrite that fixes the weakest dimensions. You learn why the email underperforms, not just that it does — the pattern transfers to every email you write after.

Any LLMGet prompt →
Reply & Objection HandlingBeginner

Handle 'we already have a vendor' without trashing the competitor

Turns the most common outbound objection into a wedge conversation. Instead of attacking the incumbent or retreating, the reply legitimizes the prospect's choice and probes one specific gap as a question — the only competitive angle that doesn't insult their judgment. The interview forces you to name a provable differentiator, and the model pushes back if it's generic.

Any LLMGet prompt →
Account & Prospect ResearchBeginner

Scan an account for trigger events: news, funding, leadership moves, layoffs

Runs a structured six-month trigger-event sweep on one account — funding, leadership changes, layoffs, launches, expansion, legal news — and returns a dated, sourced signal log, the top three events ranked by outreach value, a ready-to-adapt angle for the best one, and an honest timing call including 'no trigger exists.' It turns 'why now' from a guess into evidence.

Claude, ChatGPT, GeminiGet prompt →
Personalization at Scale (Clay & Claygents)Advanced

Turn a Claygent website scrape into a personalized one-liner

Produces a sub-25-word, website-specific opening line for every row in a Clay table — no human in the loop. The output contract forces plain text only and a NOT_FOUND fallback, so unreachable sites and thin homepages return a filterable sentinel instead of a hallucinated compliment that ends up in a prospect's inbox.

Claude, ChatGPT, GeminiGet prompt →
Cold Email WritingBeginner

Write a complete cold email from scratch

Produces a complete, send-ready cold email of 60-100 words with the four-part spine that books meetings: reason, problem, proven outcome, soft ask. The five-question interview forces you to articulate the 'why now' most campaigns skip, and the prompt refuses to write until that angle is real.

Any LLMGet prompt →
Follow-Ups & SequencesBeginner

Write value-add bump emails that never say 'just following up'

Produces touch 2 and touch 3 bump emails that each introduce a new angle — proof, insight, or resource — instead of re-asking for attention. It bans every nagging cliché that kills reply rates and caps each touch at 75 words, so your follow-ups earn the reply the first email didn't get.

Any LLMGet prompt →
Sales Copywriting & AssetsIntermediate

Align your cold email and landing page so the click doesn't break the story

Audits your cold email and landing page side by side, finds where the story breaks between click and page, and fixes the cheaper side with minimum edits. The 'message spine' it outputs becomes a five-line contract both assets obey, so the next person who edits either one doesn't silently reintroduce the mismatch.

Any LLMGet prompt →
Reply & Objection HandlingBeginner

Answer 'who are you and how did you get my email?' without panicking

Defuses the trust challenge that most reps fumble into a spam complaint. The reply answers the literal question honestly, shows the specific reason they were researched, restates the value in one plain sentence, and offers a genuine opt-out — the combination that converts challengers into conversations while protecting your domain reputation.

Any LLMGet prompt →
Personalization at Scale (Clay & Claygents)Intermediate

Audit a batch of AI first lines before the campaign sends

Catches the failure modes that only show up across a batch — recycled constructions, swap-test failures, unverifiable claims — before prospects see them. You get a grade, pattern counts, individually flagged lines, and three paste-ready fixes for the generating prompt, turning QA from a vibe check into a repeatable gate.

Any LLMGet prompt →
Cold Email WritingBeginner

Audit and rank your subject lines before you hit send

Puts every subject line candidate through a brutal pre-send audit: a 1-10 plausibility score, its biggest weakness named, spam-pattern flags, and a fixed rewrite. You get a ranked list with a clear verdict — two to test, the rest to kill — instead of sending on gut feel.

Any LLMGet prompt →
Follow-Ups & SequencesIntermediate

Audit your existing sequence like a cold email strategist

Runs your pasted sequence through a strategist-grade audit: a 7-dimension scorecard, the three biggest problems with your exact lines quoted and rewritten, a keep-revise-cut verdict per touch, and one structural recommendation. It's the outside review most teams never get before burning a list on a weak sequence.

Any LLMGet prompt →
Sales Strategy & PlanningBeginner

Build a 13-week outbound campaign calendar for the quarter

Turns a pile of campaign ideas into a staggered 13-week execution calendar with owners, prep time scheduled before launches, standing review rhythms, and kill criteria at week 7. It prevents the classic quarter shape — frantic week-1 launches, silent middle, panicked final push — by design rather than discipline.

Any LLMGet prompt →
Reply & Objection HandlingAdvanced

Build a complete AI reply-agent system prompt for your cold email inbox

Builds the production artifact most teams get wrong: the full system prompt powering an AI agent that answers your cold email replies. The interview extracts your real voice from actual sent emails, defines per-category playbooks, and hard-codes the guardrails — no invented pricing, no replies to hostility, explicit escalation JSON — so the agent is safe enough to actually deploy, not just demo.

Claude, ChatGPT, GeminiGet prompt →
Automation & Workflow DesignIntermediate

Build a deliverability monitoring workflow you actually run

Turns deliverability from vibes into a maintenance schedule: time-budgeted daily, weekly, and monthly checks with the mechanics specified, numeric if-then decision rules a non-expert can execute, a trend log, and a clear split between what n8n automates and what needs human eyes. Designed to still be running in month six.

Any LLMGet prompt →
Sales Strategy & PlanningIntermediate

Build a messaging test plan: what to A/B and in what order

Replaces random subject-line tinkering with a prioritized test program. It diagnoses which level of your messaging is actually broken, sequences eight weeks of single-variable tests with sample sizes and decision rules, and gives you a results log — so every send teaches you something instead of just burning list.

Any LLMGet prompt →
Personalization at Scale (Clay & Claygents)Intermediate

Clean up company names for email merge fields

Converts raw vendor and CRM company names into the natural short form that reads like a human typed it — no 'LLC', no ALL CAPS, no taglines — so 'quick question about {company}' merges cleanly. One of the highest ROI-per-token prompts in outbound: every recipient sees this field.

Any LLMGet prompt →
ICP, Targeting & Lead ScoringBeginner

Create persona cards for every buying role you sell to

Produces working persona cards for every role in your deals — built on metrics, pains, language, and objections rather than demographic fluff. Each card ends in a concrete outreach angle and channel, so the personas plug straight into email copy, call prep, and sequence design instead of gathering dust in a strategy doc.

Any LLMGet prompt →
Account & Prospect ResearchBeginner

Decode what a company's open roles reveal about its problems

Reads a company's open roles as evidence: what the hiring pattern says about scaling and rebuilding, which specific problems the postings confess to, what tools they name, what leadership vacancies mean for your deal, and the two best outreach hooks tied to it all. Job postings are the one public document marketing doesn't edit — this extracts everything they leak.

Any LLMGet prompt →
Reply & Objection HandlingBeginner

Defuse angry and unsubscribe replies with an exit that protects your domain

Produces the two-sentence exit that keeps an angry prospect from escalating to a spam complaint — the deliverability event that actually damages your sending domain. Past-tense removal confirmation, zero defensiveness, zero selling. Includes the full suppression checklist and CRM note so the contact never resurfaces in anyone's sequence, plus a legal-language flag when replies mention GDPR or CCPA.

Any LLMGet prompt →
Automation & Workflow DesignIntermediate

Design QA guardrails for AI-generated outreach before it sends

Builds a pre-send QA layer for AI outreach: automated factual, personalization, format, and compliance checks with detection logic written out, a volume-appropriate human sampling plan, a severity ladder, an automatic kill switch, and a weekly feedback loop that turns caught failures into permanent prompt fixes.

Claude, ChatGPT, GeminiGet prompt →
Negotiation, Proposals & ClosingIntermediate

Design a win-back offer for a churned customer

Builds a win-back play that starts from why the customer actually left: a churn classification, a change story answering that specific reason, an offer designed around the failure rather than a blanket discount, and a 100-word no-groveling email with timing mapped to their replacement vendor's contract cycle.

Any LLMGet prompt →
Automation & Workflow DesignAdvanced

Design alerting for your outbound infrastructure before it burns

Designs a complete monitoring layer for sending infrastructure: a per-domain metric catalog, volume-tuned warning and critical thresholds, check cadences with the tool that runs each, anti-fatigue alert routing, runbooks for the five likeliest incidents, and a weekly drift digest. Problems surface in hours instead of after a burned domain.

Any LLMGet prompt →
Automation & Workflow DesignIntermediate

Design an A/B test automation for your outbound campaigns

Builds an outbound testing system honest about statistical power: a testability check that kills underpowered tests before they waste weeks, single-variable test templates with minimum samples and stopping rules, sequencer-level automation mechanics, and a learning log so wins compound. Its distinguishing feature is telling you what not to test at your volume.

Any LLMGet prompt →
ICP, Targeting & Lead ScoringAdvanced

Design an ICP hypothesis testing plan for a new product

Turns 'who should we sell this to?' from a debate into an experiment: explicit ICP hypotheses with reasoned mechanisms, head-to-head outbound test designs sized to your capacity, and pre-committed confirm/kill thresholds that prevent goalpost-moving. The learning log ensures even failed tests compound into targeting knowledge.

Any LLMGet prompt →
Follow-Ups & SequencesIntermediate

Diagnose why your sequence isn't getting replies

Isolates why your sequence underperforms by walking your funnel numbers through the four possible causes — deliverability, targeting, message, offer — and names the most likely one with reasoning and confidence, ranked fixes, and a cheap test to falsify the diagnosis. It stops you rewriting copy when the real problem is the inbox never showing it.

Any LLMGet prompt →
Cold Email WritingBeginner

Distill your value prop into one cold-email-ready sentence

Forces your value proposition through a compression process that ends with one falsifiable sentence under 22 words — who it's for, the outcome, and a number or mechanism no competitor could claim. You get 5 ranked candidates with tradeoff notes, ready to drop into every cold email you write.

Any LLMGet prompt →
Sales Copywriting & AssetsIntermediate

Extract a brand voice guide from your five best-performing emails

Reverse-engineers a usable voice guide from the five emails that already earned replies — fingerprint, vocabulary map, evidence-cited tone rules, a 'never' list, and a paste-ready system prompt block for AI drafting. Every rule cites your actual copy, so the guide describes the voice that works instead of the voice a workshop wished you had.

Any LLMGet prompt →
Personalization at Scale (Clay & Claygents)Intermediate

Find a company's most recent news or press mention

Finds one verified, recent, sales-usable news item per account and returns it as structured JSON with date, source, URL, and a merge-ready one-liner. The identity check and 120-day window prevent the two classic failures: referencing another company's news, or congratulating someone on a two-year-old raise.

Claude, ChatGPT, GeminiGet prompt →
Account & Prospect ResearchBeginner

Find the outreach angle hidden in a company's recent news

Works recent company news through a four-step chain — event, consequence, internal pressure, bridge to your offer — instead of stopping at 'congrats on the news.' You get dated and sourced usable items, fully reasoned angle chains, three distinct openers for the best one, and a skip list of items that would hurt to reference.

Claude, ChatGPT, GeminiGet prompt →
Follow-Ups & SequencesBeginner

Follow up on a content download without the 'did you read it' cringe

Turns a content download into a 3-touch sequence that extends the topic instead of pouncing on weak intent — bonus insight first, practice bridge second, honest sort third. It filters real buyers out of curious readers without the surveillance-flavored follow-ups that make downloaders regret giving an email.

Any LLMGet prompt →
Cold Email WritingBeginner

Generate 10 cold email opening lines from one piece of research

Turns a single piece of prospect research into 10 labeled opening lines, each under 25 words and each connecting an observation to a business problem. You get angle variety on demand instead of staring at a blank compose window, plus the model's pick of the two strongest lines with reasoning.

Any LLMGet prompt →
Cold Email WritingIntermediate

Generate A/B test variants of your best cold email

Turns your control email into a disciplined test plan: a diagnosis of its current mechanics, four variants that each isolate one variable — angle, proof, CTA, or opener — and a ranked prediction of which to test first. It also checks whether your send volume can even power a meaningful result.

Any LLMGet prompt →
Cold Email WritingBeginner

Generate PS lines that earn a second read

Generates 8 PS lines across the five jobs a PS can do — proof, objection-disarm, easy-out, curiosity, and human — then pairs the best one to your specific email with reasoning. It turns the most-read line in cold email from an afterthought into a deliberate second hook.

Any LLMGet prompt →
Cold Email WritingBeginner

Generate cold email subject lines that get opened

Generates 12 short, lowercase subject lines across four strategic types, each annotated with its risk, plus a top-three pick for your audience. It replaces the guess-and-hope subject line habit with a structured set you can rotate through A/B tests, and warns you when the email body is the real problem.

Any LLMGet prompt →
Cold Email WritingIntermediate

Generate industry-specific cold email angles

Produces a complete vertical angle brief: five industry-specific ways into a cold email written in the buyer's own vocabulary, language do's and don'ts, what proof that industry finds credible, and a ranked recommendation. It's positioning translation for verticals — not your horizontal pitch with an industry label stapled on.

Any LLMGet prompt →
Account & Prospect ResearchIntermediate

Generate ranked pain hypotheses for an account from public signals

Converts a pile of raw public signals into 4-6 falsifiable pain hypotheses, each graded by evidence strength, costed if true, and ranked by fit with your product — plus the discovery question and email opener that would test the top two. It replaces persona-based guessing with evidence-based hypotheses you can confirm or kill in one conversation.

Any LLMGet prompt →
Call Transcript Analysis & CoachingIntermediate

Generate the follow-up email directly from the call transcript

Drafts the post-call email straight from the transcript: opens with the prospect's own most important point, advances exactly one thread instead of recapping everything, honors every commitment made on the call, and locks a dated next step. The not-included list explains what it left out so you don't stuff it back in.

Any LLMGet prompt →
Reply & Objection HandlingBeginner

Handle 'talk to my colleague' referrals without losing the thread

Converts a referral reply into two precise emails: one that thanks the referrer while extracting intel and removing all work from their plate, and one to the colleague that spends the endorsement correctly — explicit, factual, and calibrated to whether the referral came from a boss or a peer. Referral threads convert at multiples of cold outreach; this stops them dying in the handoff.

Any LLMGet prompt →
Account & Prospect ResearchIntermediate

Infer a prospect's tech stack and what it says about their pain

Turns raw tech-stack evidence — BuiltWith exports, tool mentions in job posts, integration pages — into a confidence-labeled read of what a prospect runs, what they almost certainly also run, and what it reveals about budget, maturity, and gaps your product fills. It converts a list of logos into a fit assessment and a credible talk track.

Any LLMGet prompt →
Cold Email WritingAdvanced

Match your cold email to a prospect's writing style

Profiles a prospect's public writing across five stylistic dimensions, then writes your cold email in their register — their rhythm and formality carrying your offer and proof. The calibration note shows exactly where it mirrored and where it held back, keeping the technique on the rapport side of the creepy line.

Any LLMGet prompt →
Account & Prospect ResearchIntermediate

Mine G2 reviews of a prospect's product to learn their pains

Mines public reviews of your prospect's own product to reveal what their internal teams get beaten up about: complaint clusters with frequency and severity, who inside the company owns each pain, whether it's growing, and which pains your product genuinely addresses. It's discovery intel gathered before anyone takes your call.

Any LLMGet prompt →
Account & Prospect ResearchIntermediate

Mine a 10-K or annual report for the pain your product solves

Turns a 10-K or annual report into a seller's cheat sheet: admitted pains with section references, implied pressures, strategic bets, and verbatim quotable lines mapped to the outcome you sell. It replaces two hours of skimming dense filing language with a focused read that flags weak fits honestly instead of forcing connections.

Claude, GeminiGet prompt →
Personalization at Scale (Clay & Claygents)Intermediate

Mine a local business's website for outreach signals

Builds a structured profile of any local business from its website: type, service area, owner name, tenure claim, self-stated differentiator, booking capability, and one outreach hook. It gives local-market campaigns the specificity that owner-operators respond to, at a volume no rep could research by hand.

Claude, ChatGPT, GeminiGet prompt →
Personalization at Scale (Clay & Claygents)Intermediate

Mine case-study pages for named customers and results

Turns any customers or case-study page into structured proof data: up to three named customers with their claimed results, plus a visible-customer count. Use it to personalize with 'you already serve teams like X', to map a competitor's install base, or to score accounts by proof maturity.

Claude, ChatGPT, GeminiGet prompt →
Cold Email WritingIntermediate

Re-engage closed-lost prospects without sounding desperate

Reopens closed-lost accounts with a change-led email instead of a guilt-tinged check-in. It acknowledges the old deal in one clause, leads with what's genuinely different since they passed, and refuses to send at all when nothing has changed — protecting the asset that makes this channel work: they already know you.

Any LLMGet prompt →
Follow-Ups & SequencesBeginner

Re-engage prospects who went dark 90 days ago

Builds a 3-touch sequence that revives 90-day-dark prospects by leading with what's new instead of apologizing for the gap. It uses their original interest as quiet context, adds proof mid-sequence, and closes with a question that's easy to answer either way — turning a dead list segment back into working pipeline.

Any LLMGet prompt →
Reply & Objection HandlingBeginner

Reply to a 'not interested' response without arguing or groveling

Drafts a calm, three-sentence response to 'not interested' that neither argues nor apologizes — the two failure modes that kill these threads. The interview pulls in the original email and the prospect's exact words, so the reframe targets the likely real objection instead of generically begging for reconsideration. You also get a graceful close-out version.

Any LLMGet prompt →
Account & Prospect ResearchIntermediate

Research the regulatory pressure bearing down on an industry you sell into

Builds a seller's map of the regulatory pressure on an industry: which rules actually apply and to whom, the deadline calendar with hard dates flagged, what enforcement realistically costs, which roles carry each burden, and honest lines connecting your product to the two most relevant pressures — plus a verify-before-using list, because compliance-literate buyers punish sloppy claims.

Claude, ChatGPT, GeminiGet prompt →
Cold Email WritingBeginner

Rewrite a bloated cold email to under 75 words

Compresses an overweight cold email to under 75 words through a visible sentence-by-sentence audit — KEEP, MERGE, or CUT — followed by a rewrite that preserves your voice and strongest proof. The audit teaches you what to stop writing; the flag list tells you what belongs in a later touch instead.

Any LLMGet prompt →
Sales Copywriting & AssetsBeginner

Rewrite every CTA on your site from 'Learn more' to copy that converts

Sweeps every button and link CTA across your site or emails and rewrites each into specific, next-step-honest copy with anxiety-reducing microcopy underneath. You get a ranked table of rewrites plus a first-person A/B candidate, instead of another round of 'Learn more' surviving a redesign because nobody owned the buttons.

Any LLMGet prompt →
Sales Copywriting & AssetsIntermediate

Script a 60-90 second video sales letter that earns the meeting

Scripts a timed 60-90 second VSL — hook by second eight, problem, mechanism, proof, single ask — as a two-column script with spoken words and per-section visual notes, plus a thumbnail title and two alternate hooks. Written for the ear at natural speaking pace, so it records in one take instead of reading like an essay.

Any LLMGet prompt →
Cold Email WritingBeginner

Scrub spam trigger words without killing your message

Audits your cold email for deliverability risk across five categories — trigger words, salesy patterns, formatting, links, and HTML — then rewrites it clean without flattening your message into corporate mush. The residual-risk note tells you when the problem is your infrastructure, not your copy.

Any LLMGet prompt →
Reply & Objection HandlingBeginner

Tone-check and stress-test a drafted reply before you hit send

The pre-send check reps skip: reads your drafted reply the way the prospect will receive it, flags neediness, defensiveness, energy mismatch, and leverage giveaways with the exact phrases quoted, then rewrites in your voice — calmer. Crucially, it's instructed to say 'send it' when the draft is fine instead of inventing edits, so you can trust the flags it does raise.

Any LLMGet prompt →
Sales Copywriting & AssetsBeginner

Translate your feature list into a benefit table sellers can quote

Runs every feature through the full translation chain — feature, advantage, buyer benefit, cost of lacking it, and a quotable sentence per persona — then routes the three strongest rows to specific assets and honestly flags parity features not worth leading with. It turns the raw feature list into language sellers can actually say out loud.

Any LLMGet prompt →
Reply & Objection HandlingBeginner

Turn 'send me more info' into a meeting instead of a dead PDF

Converts the classic brush-off into a qualification step. Instead of firing a deck into the void, the reply agrees warmly, asks one 'so I send the right thing' question, offers a small specific artifact, and positions a 15-minute call as the lazier option for the prospect. Includes the 4-day silent-reader follow-up most reps forget to send.

Any LLMGet prompt →
Cold Email WritingBeginner

Turn a customer case study into a cold email

Compresses a full case study into a sub-90-word cold email built around one before-and-after sentence with a real number. It handles the anonymization question, bans the 'attached is a case study' pattern that kills replies, and offers the story as the CTA — so the proof does the selling instead of a pitch.

Any LLMGet prompt →
Personalization at Scale (Clay & Claygents)Intermediate

Turn one case study into 5 segment-specific angles

Multiplies your best proof asset by five: each angle re-frames the same defensible facts for a different segment's actual concern, with a ready cold email line and the objection it quietly answers. It stops the one-size-fits-nobody case study line and stays strictly inside what you can prove.

Any LLMGet prompt →
ICP, Targeting & Lead ScoringIntermediate

Turn your ICP into messaging pillars for every campaign

Converts your ICP into 3-4 messaging pillars — core arguments mapped to specific ICP pains, each with proof, an emotional undertone, and ready translations for email, phone, and LinkedIn. The pillar test kills generic claims any vendor could make, and the usage map tells campaigns which argument leads where.

Any LLMGet prompt →
Reply & Objection HandlingBeginner

Win over a gatekeeper or executive assistant who answered your email

Turns the gatekeeper reply most reps treat as a wall into a routing conversation with the person who actually controls access. The reply gives the EA real substance, a forwardable summary that does their job for them, and explicit deference to their judgment — the combination EAs reward. Includes the model pushing back if your relevance claim is too generic to survive screening.

Any LLMGet prompt →
Follow-Ups & SequencesBeginner

Write a breakup email that revives dead threads

Writes two structurally different breakup emails under 60 words each — one that closes the thread gracefully and one that leads with a parting gift — with guidance on which fits your situation. It bans the guilt-trip clichés that make breakup emails backfire and adapts tone for cold sequences versus stalled deals.

Any LLMGet prompt →
Cold Email WritingBeginner

Write a cold email for a boring or unsexy product

Reframes an unglamorous product around what its buyer actually feels: the consequences of failure. You get a ranked stakes analysis, a sub-90-word email that opens on the moment things go wrong rather than the product category, and a second consequence angle to test against the first.

Any LLMGet prompt →
Cold Email WritingIntermediate

Write a cold email from a prospect's tech stack

Converts raw technographic data into ranked implications about how the prospect operates, then writes a sub-85-word email that leads with the implied friction instead of reciting their tool list. It draws the line between insight and surveillance, and tells you when your stack data is too generic to use.

Any LLMGet prompt →
Cold Email WritingIntermediate

Write a cold email to enterprise buyers

Produces a cold email calibrated to enterprise physics: initiative-aware opening, outcomes framed as risk reduction in the buyer's currency, peer-grade proof, and an org-chart-respecting CTA that invites routing to the right owner. It also tells you when your proof isn't enterprise-credible yet, instead of letting you overclaim.

Any LLMGet prompt →
Cold Email WritingBeginner

Write a cold email to event and webinar attendees

Turns event attendance into a topic-continuation email instead of a fake reunion. The email opens with what attendance implies the prospect is working on, connects it to your offer with proof, and closes by advancing the event's conversation — while banning every 'great to connect' move that poisons this channel.

Any LLMGet prompt →
Cold Email WritingBeginner

Write a cold email to startup founders

Writes a sub-70-word, phone-readable email in founder physics: stage-specific pain in the first line, one outcome with a number in founder currency, and a five-second binary CTA. It bans the 'love what you're building' opener every founder has deleted a hundred times and pushes you past generic startup platitudes.

Any LLMGet prompt →
Cold Email WritingBeginner

Write a cold email triggered by a funding announcement

Turns funding news into an email about what the money obligates the company to do — the hiring, the targets, the strain — instead of joining the congrats flood. You get the obligation diagnosis, a sub-90-word email that never says 'congrats', and a send-timing recommendation for your offer type.

Any LLMGet prompt →
Cold Email WritingBeginner

Write a cold email triggered by a job posting

Converts a job posting into a diagnosis of the initiative behind it, then into a sub-90-word email that speaks to that initiative rather than reciting 'saw you're hiring'. It forces you to pick the honest angle — make the hire succeed, ramp faster, or become unnecessary — and refuses forced connections.

Any LLMGet prompt →
Cold Email WritingIntermediate

Write a cold email when you have no personalization signal

Solves the no-signal prospect problem with segment-level precision instead of fake personalization. You get an under-80-word email whose opening problem statement is so specific to the role and industry that it reads as researched — the honest, scalable alternative to 'I was browsing your website'.

Any LLMGet prompt →
Cold Email WritingIntermediate

Write a competitor displacement cold email

Builds a displacement email around one felt limitation of the prospect's current tool — surfaced as a stage-based observation, not an attack. You get the wedge analysis, a sub-90-word email with a switcher proof point, and honest handling of the case where your real advantage is price, not capability.

Any LLMGet prompt →
Personalization at Scale (Clay & Claygents)Intermediate

Write a personalized opener from a trigger event

Converts trigger events into two-sentence openers built on the event-to-consequence structure that separates trigger-based outbound from the congratulations flood. Role-aware consequence logic means the same funding round produces different openers for a CFO and a VP of Sales — automatically, per row.

Any LLMGet prompt →
Sales Copywriting & AssetsBeginner

Write a webinar invitation that sells the takeaway, not the event

Produces a complete webinar promotion kit — three outcome-led titles, a sub-150-word invitation, a day-before reminder, a registration blurb, and an honest recording line — all selling what attendees walk away with rather than the event itself. The interview forces concrete takeaways out of you before a word gets written.

Any LLMGet prompt →
LinkedIn & Social SellingIntermediate

Write an InMail that actually gets a reply

Writes a sub-100-word InMail with a notification-optimized subject line and an observation-led opener, honest about being cold instead of faking familiarity. Because InMail costs credits per send, the interview forces a real trigger before you spend one — the model will tell you when you don't have a reason to reach out yet.

Any LLMGet prompt →
Cold Email WritingBeginner

Write an ultra-short three-sentence cold email

Delivers three complete cold email variants of exactly three sentences and at most 45 words each — one sentence for relevance, one for proven value, one for a frictionless ask. The format that respects busy readers most, engineered so no sentence hides behind another and vague claims have nowhere to live.

Any LLMGet prompt →
Sales Copywriting & AssetsIntermediate

Write guarantee and risk-reversal copy that closes fence-sitters

Selects the right risk-reversal structure for your delivery reality — outcome guarantee, work-free-until, pilot criteria, or money-back — then writes the guarantee statement, honest terms block, and three placement versions. It sizes the promise on your worst-quartile results and shows what a 10% claim rate costs, so you offer confidence you can actually honor.

Any LLMGet prompt →
Sales Copywriting & AssetsBeginner

Write landing page hero copy that survives the five-second test

Produces three genuinely different hero sections — headline, subhead, CTA with microcopy, and proof strip placement — then self-grades them against the five-second test and picks a winner. Because it asks where traffic comes from, the copy matches the visitor's intent instead of restating your org chart's favorite tagline.

Any LLMGet prompt →
Sales Copywriting & AssetsBeginner

Write nurture emails that teach instead of pitch

Writes a 5-email nurture sequence where the first four emails deliver standalone insights — benchmarks, mistakes, mini-cases — and only the fifth asks for anything. Each email is under 150 words with timing notes, built from what you actually know about your buyer's world, so leads stay warm without being 'checked in on'.

Any LLMGet prompt →
LinkedIn & Social SellingBeginner

Write outreach to attendees of an event, webinar, or conference

Produces a full event outreach kit — pre-event connection notes, post-event DMs built on actual session content, a follow-up, and a message for registered no-shows. It refuses to write attendance-scraper spam: if you can't name one specific thing from the event, it sends you back to the recording first.

Any LLMGet prompt →
Cold Email WritingIntermediate

Write personalized first lines for an entire prospect list

Processes a pasted prospect list and returns a spreadsheet-ready table of first lines, each under 22 words and built from that row's data. Weak rows get flagged instead of padded with filler, so you know exactly which prospects need more research before they enter your sequence.

Claude, ChatGPT, GeminiGet prompt →
LinkedIn & Social SellingBeginner

Write the first DM after a connection is accepted (without pitch-slapping)

Produces a sub-50-word opener that starts a real conversation with a new connection instead of triggering the mute button, plus the reply-to-their-reply message so you're not improvising when it works. The interview forces you to articulate a reason to talk that isn't your pitch — which is the whole game.

Any LLMGet prompt →
Cold Calling Scripts & OpenersIntermediate

Write the follow-up call script for prospects who engaged with your email

Turns email engagement signals into three call scripts, one each for open clusters, link clicks, and soft replies, that use the intelligence without ever revealing the tracking. Each stays under 50 words before the prospect speaks, with branches for interest and brush-off. It converts your warmest dials without the surveillance vibe that kills them.

Any LLMGet prompt →
Cold Email Writing FAQ

Frequently asked questions

Yes, but only with the right constraints. Left alone, ChatGPT writes long, flattering, feature-heavy emails that prospects delete. These prompts fix that by enforcing word caps, banning the clichés everyone recognizes as AI, and requiring an observation-to-problem structure. The interview format also forces you to supply real context, which is what separates a researched email from a generic one.

Want this running on autopilot instead?

We wire prompts like these into a full outbound system — data, personalization, sending, and replies orchestrated end to end. You own the infrastructure. We guarantee the results.

Apply for a Pilot Spot →