AI cold email prompts help US B2B senders — SDRs, founders doing their own outbound, agency owners, and solo consultants — draft the specific messages that make a cold sequence actually convert. First-touch emails, 10 subject-line A/B variants, a LinkedIn-personalized opener, follow-up 2 through 4, the breakup email, and the responses to 'send me info' and 'not interested' are all in this library, tuned for US B2B norms.
Every template below is written for the US cold email context: CAN-SPAM Act compliance (accurate sender identity, valid physical mailing address, working unsubscribe, no deceptive subject lines), US business hours (Tuesday–Thursday sends between 8–11am local recipient time), and typical mid-market and enterprise reply-rate baselines of 1–4%. Deliverability assumes a warmed sending domain, SPF/DKIM/DMARC set up correctly, and sub-40 sends per mailbox per day.
This content is educational only and is not legal advice. CAN-SPAM violations can be enforced by the FTC at up to $50,000+ per violation; state-level laws (notably California's CCPA/CPRA and Delete Act) add further requirements. B2B cold email is legal in the US under CAN-SPAM as long as compliance is followed, but sending to EU or UK recipients requires GDPR/PECR-compliant opt-in. When in doubt, consult a marketing attorney or your DPO before scaling outbound.
AI cold email prompts help US B2B senders — SDRs, founders doing their own outbound, agency owners, and solo consultants — draft the specific messages that make a cold sequence actually convert. First-touch emails, 10 subject-line A/B variants, a LinkedIn-personalized opener, follow-up 2 through 4, the breakup email, and the responses to 'send me info' and 'not interested' are all in this library, tuned for US B2B norms.
Every template below is written for the US cold email context: CAN-SPAM Act compliance (accurate sender identity, valid physical mailing address, working unsubscribe, no deceptive subject lines), US business hours (Tuesday–Thursday sends between 8–11am local recipient time), and typical mid-market and enterprise reply-rate baselines of 1–4%. Deliverability assumes a warmed sending domain, SPF/DKIM/DMARC set up correctly, and sub-40 sends per mailbox per day.
This content is educational only and is not legal advice. CAN-SPAM violations can be enforced by the FTC at up to $50,000+ per violation; state-level laws (notably California's CCPA/CPRA and Delete Act) add further requirements. B2B cold email is legal in the US under CAN-SPAM as long as compliance is followed, but sending to EU or UK recipients requires GDPR/PECR-compliant opt-in. When in doubt, consult a marketing attorney or your DPO before scaling outbound.
Guides, tips, and deep dives for this prompt category
Create stunning Studio Ghibli-style AI art with 50 free prompts for ChatGPT. Magical landscapes, characters, food scenes, and cozy interiors in Miyazaki style.
Read moreAI PromptsThe best free AI prompt library in 2026. Browse 4,000+ tested prompts for Midjourney, DALL-E 3, Stable Diffusion, FLUX, and ChatGPT. No signup, no paywall — copy and create instantly.
Read moreCopy any prompt below, paste into ChatGPT, Claude, Gemini, or Copilot, and fill in the placeholders in [brackets].
Act as a US B2B cold email copywriter. Write a first-touch cold email to a [title] at a [industry] company with [employee count] employees in the US. Reference one specific trigger (funding, hire, product launch, public initiative) and offer one specific insight the recipient likely has not seen. Close with a single 15-minute meeting ask on a named day. Plain text, under 100 words, no images, no marketing footer.
Act as a US B2B email A/B testing strategist. Write 10 subject line variants for a cold email offering a [product / benchmark / audit / intro call] to [title] at US [industry] companies. Split them across 4 styles: (1) 2 curiosity-driven, (2) 3 specific-number driven, (3) 3 pain-first, (4) 2 low-key first-name-only. Each under 55 characters. No emoji, no ALL CAPS, no spam triggers.
Act as a US B2B outbound rep. Write a personalized opener line (single sentence) for a cold email to [title] at [company], based on this specific LinkedIn signal: [paste post / hire / recent role change / article they wrote]. The opener must sound like a peer noticed the specific thing, not like a mail-merged compliment. Give 3 variants ranging from casual to more formal.
Act as a US B2B cold email sequence writer. Write follow-up emails #2, #3, and #4 for a 4-touch sequence targeting [title] at [industry] US companies. Follow-up #2 (3 business days after first touch, under 60 words): different angle, restate the ask. Follow-up #3 (5 business days later, under 90 words): offer a specific piece of value (benchmark, teardown, case study) that requires no call. Follow-up #4 (7 business days later): last value-add before the breakup, one specific insight tied to their quarterly priority. Do not use 'circling back' or 'bumping this up.'
Act as a US B2B cold email closer. Write a breakup email (final touch in a sequence, sent 5 business days after follow-up #4) to [title] at [company]. Under 40 words, no guilt, no passive aggression. Acknowledge that timing may not be right, offer one graceful out (a future check-in in 6 months), and ask a single yes/no question that makes it easy for them to reply with either a yes or a polite no.
Act as a US B2B outbound rep. Write a reply to a prospect who responded to a cold email with 'send me more info.' In 3 sentences, reframe the ask as a 15-minute discovery call because a personalized walk-through beats a generic PDF for their specific use case. If they still insist, attach one 1-page overview and re-ask for the call in the same email. Keep it warm, not defensive.
Act as a US B2B outbound rep. Write a reply to a prospect who responded to a cold email with 'not interested.' Do not argue, do not double down, do not try to overcome the objection. Instead, thank them briefly, ask one diagnostic question about which of 3 things it was (timing, existing solution, not the right person), and offer to remove them from the sequence. Under 50 words.
Act as a US B2B outbound rep. Write a follow-up email to a prospect who received a warm intro from a mutual contact but has not replied in 5 business days. Reference the intro without over-relying on it, restate the specific ask from the introducer's email, add one new piece of information relevant to the prospect, and close with a proposed 20-minute meeting on two named days. Under 130 words.
Act as a US B2B outbound rep. Write a referral cold email to a target prospect where a shared connection has agreed to be used as a reference but is not making a direct introduction. Lead with the shared connection's name and how you know them, one specific reason they suggested reaching out, the value prop in one sentence, and a low-friction ask. Under 110 words.
Act as a US B2B event follow-up rep. Write a post-event follow-up email to a prospect who visited the booth or attended the demo at [event name] on [date]. Reference one specific conversation moment (a question they asked, a product feature they liked), add one specific piece of information that answers the follow-up they mentioned wanting, and propose a 20-minute call within the next 10 business days.
Act as a US B2B outbound strategist. Draft a decision guide for when to use LinkedIn InMail vs. email for cold outbound to [title] at [company profile]. Compare: (1) reply-rate benchmarks, (2) character limits and formatting, (3) how the recipient perceives each channel, (4) cost per touch, (5) how to sequence a multi-channel play (e.g., LinkedIn view → connection request → email → InMail). Include 2 recipient personas where InMail wins and 2 where email wins.
Act as a US CAN-SPAM and email compliance advisor. Produce a 12-item pre-send compliance checklist for a US B2B cold email campaign. Include: accurate sender identity, non-deceptive subject line, clear commercial-message disclosure (if applicable), valid physical mailing address, working unsubscribe, honor unsubscribes within 10 business days, no purchased-list violations, domain SPF/DKIM/DMARC configured, DMARC alignment, sending volume per mailbox per day, warmup schedule for new domains, suppression list hygiene.
Act as a US B2B outbound RevOps analyst. Design a personalization-at-scale system for a sending team of [number] SDRs targeting [number] prospects per week. Cover: (1) which fields to merge (first name, company, one trigger event, one custom insight), (2) which fields to hand-write per prospect, (3) tooling — Clay / Instantly / Smartlead / Apollo / manual, (4) a QA sampling rate to catch bad merges before send, (5) a per-mailbox daily cap that keeps deliverability healthy.
Act as a US B2B outbound diagnostician. Produce a reply-rate diagnostic checklist for a cold email campaign that is running below 1% positive-reply rate. Walk through 8 root causes in order: (1) list quality and ICP fit, (2) domain and mailbox warmup status, (3) SPF/DKIM/DMARC alignment, (4) sending volume per mailbox per day, (5) subject-line spam triggers and open rate, (6) first-line personalization quality, (7) ask clarity and length, (8) time-of-day and day-of-week. For each, give the metric to check, the healthy range, and the one fix to try first.
Understanding the building blocks lets you adapt any prompt to your own creative direction.
Tell the AI who the output is for and what real workplace situation it should support.
Act as a federal program analyst preparing a plain-language memo for agency leadership.Name the exact deliverable: email, memo, checklist, SOP, meeting recap, training note, or status update.
Format the answer as a one-page briefing with bullets, risks, and next actions.Specify whether the output should sound official, executive-ready, plain-language, or employee-friendly.
Use a professional, neutral, public-sector tone suitable for a US agency audience.For government, HR, finance, healthcare, legal, and compliance workflows, accuracy guardrails matter more than clever wording.
Use only the facts below, flag assumptions, and include a section for items that need verification.Ask the model to surface uncertainty so the user can verify sensitive or official information before using it.
Before finalizing, list compliance risks, missing details, and any claims that need human review.Tested on this prompt category as of mid-2026. Ratings reflect quality for AI Cold Email Prompt Library specifically.
| Model | Best for | Rating |
|---|---|---|
| ChatGPT (GPT-4o / GPT-5) | Everyday drafting and summaries | |
| Claude Sonnet 4.5 | Long documents and policy | |
| Gemini 2.5 Pro | Grounded in Google workspace | |
| Copilot (M365) | Office 365 integration | |
| Perplexity | Answers with citations |
Ratings reflect suitability for this category. Free tiers available on all listed models. Last tested May 2026 by PromptSpace editors.
For a tight ICP list of 200–500 prospects, a warmed sending domain, and personalized copy: 1–4% total reply rate and 0.5–1.5% positive reply rate. Below 0.5% positive means the list, offer, or deliverability is broken — not the copy. Use the reply-rate diagnostic prompt to isolate which one before rewriting the email.
Yes, when compliance is followed: accurate sender identity, non-deceptive subject line, valid physical mailing address, working unsubscribe honored within 10 business days, and no misleading header info. Purchased lists and scraped emails can be sent to under CAN-SPAM but often violate GDPR (for EU recipients) and hurt domain reputation.
4–6 total touches over 14–21 business days is the norm. More than 6 damages your domain reputation and rarely produces net-new positive replies. The breakup email at the end (touch 5 or 6) often generates the highest per-touch reply rate of the entire sequence.
No. Use a dedicated sending domain (usually a variation like getcompany.com or trycompany.com) that you have warmed for 3–4 weeks before scaling. This isolates domain reputation risk from your main corporate email, which you rely on for customer and investor communication.
Tuesday, Wednesday, and Thursday between 8–11am local recipient time consistently outperforms other windows. Avoid Monday morning (inbox triage backlog) and Friday afternoon (weekend brain). Test time-of-day in your own data — the difference between best and worst window is often 30–50% on reply rate.
Learn the basics of creating stunning AI-generated images using prompts from our library.
GuideDiscover the secrets to crafting prompts that produce consistent, high-quality results.
CollectionCopy-paste 100 tested Midjourney v6 prompts: portraits, cinematic, fantasy, product shots & more. Free, updated for 2026 - instant results.
Social MediaCreate scroll-stopping Instagram content with these AI image prompts designed for Reels, Stories, and posts.
Browse our full library of ai cold email prompt library — all free, copy-paste ready, no signup.
Or use our AI Prompt Generator to create custom prompts for your exact style in seconds.
Start with the list and the segment, not the copy. Feed the AI the specific ICP (title, company size, industry, region), the one insight or trigger event you can genuinely reference, and the single call to action for this email. 'Write a cold email' produces slop; 'write a first-touch cold email to a VP Marketing at a 100–500 person US B2B SaaS that just raised a Series B in the last 60 days, offering a 15-minute call to walk through a benchmark report' produces something worth sending.
Then run every AI draft through a three-pass edit: (1) cut all filler openers ('I hope this finds you well,' 'my name is,' 'I wanted to reach out'), (2) cut adjectives that are not backed by a number, (3) confirm the ask is one specific thing with one specific verb. The single best predictor of reply rate on US B2B cold email is whether the ask is easy to say yes or no to in under 5 seconds.
A good cold email prompt names the sender (title, company one-liner, credibility signal), the recipient (title, company profile, one trigger), and the one thing you want back (15-min call, a specific reply, a warm intro). It also states the sequence position — a first touch does not look like a follow-up 3 — and the length constraint. US B2B recipients skim on mobile; a 300-word cold email is dead on arrival.
Also give the AI a rule set for personalization: name the fields you will merge in (first name, company name, recent news, mutual connection) and where they go. Fake-sounding personalization ('I love what you're doing at [company]') is worse than none. If the AI cannot say anything specific about the recipient, cut the personalization sentence entirely and lead with the insight.
A US B2B cold sequence typically runs 4–6 touches over 14–21 business days. The prompts below cover follow-up 2 (short nudge), follow-up 3 (new angle or asset), follow-up 4 (final value add), and the breakup email — which counter-intuitively has one of the highest single-touch reply rates in the entire sequence when written correctly.
The best breakup emails are short (under 40 words), do not sound passive-aggressive, offer one graceful out, and often produce a reply because the recipient's guilt reflex kicks in. The template below is written for that specific psychology. Do not send more than one breakup email in a sequence — that is not a breakup, it is nagging, and it damages both your domain reputation and your brand.
Everything in this library assumes your deliverability infrastructure is set up correctly: a dedicated warmed sending domain (not your primary), SPF, DKIM, and DMARC records passing, an unsubscribe link on every email, and a physical mailing address in the footer per CAN-SPAM §316.4. Without that foundation, even a perfect email lands in spam and never generates a reply — you will misdiagnose a deliverability problem as a copy problem and iterate on the wrong thing.
The reply-rate diagnostic prompt below walks through the 8 things to check before you touch the copy again — list quality, ICP fit, sending volume per mailbox, domain reputation, subject line spam triggers, first-line personalization quality, ask clarity, and time-of-day. If your reply rate is under 1%, it is almost never the copy alone.
For a tight ICP list of 200–500 prospects, a warmed sending domain, and personalized copy: 1–4% total reply rate and 0.5–1.5% positive reply rate. Below 0.5% positive means the list, offer, or deliverability is broken — not the copy. Use the reply-rate diagnostic prompt to isolate which one before rewriting the email.
Yes, when compliance is followed: accurate sender identity, non-deceptive subject line, valid physical mailing address, working unsubscribe honored within 10 business days, and no misleading header info. Purchased lists and scraped emails can be sent to under CAN-SPAM but often violate GDPR (for EU recipients) and hurt domain reputation.
4–6 total touches over 14–21 business days is the norm. More than 6 damages your domain reputation and rarely produces net-new positive replies. The breakup email at the end (touch 5 or 6) often generates the highest per-touch reply rate of the entire sequence.
No. Use a dedicated sending domain (usually a variation like getcompany.com or trycompany.com) that you have warmed for 3–4 weeks before scaling. This isolates domain reputation risk from your main corporate email, which you rely on for customer and investor communication.
Tuesday, Wednesday, and Thursday between 8–11am local recipient time consistently outperforms other windows. Avoid Monday morning (inbox triage backlog) and Friday afternoon (weekend brain). Test time-of-day in your own data — the difference between best and worst window is often 30–50% on reply rate.