AI can make cold outreach better. This isn’t a debate anymore. And if you’re using Hunter, then you’re already leveraging AI which we’ve implemented across the platform.

Through our research, we found that 67% of decision makers don’t care if you use AI to write your cold emails.

At the same time, there’s a problem with how AI is used in cold email.

The emails that I tend to get nowadays:

  • Are packed with AI buzzwords,
  • Use irrelevant AI-powered personalization.

Writing personalized openers is a common AI use case for cold email, but does it really make cold emails more relevant?

AI has its place in your cold email toolset, but we shouldn’t use it for automation only. It can and should serve to make your messaging more relevant in a scalable way.

In this article, I’ll share specific use cases AI has in the context of cold email, and how to prompt it to give you what you need, from copywriting to researching your ICP and evaluating your sequence.

Write cold email copy with AI

We’ve all seen AI slop, but it doesn’t change the fact that AI is great at writing. It’s fast, the quality of its output is directly proportional to the effort you put into your prompts, and with sufficient prompting, its writing can truly impress.

There are two problems, though, when you try writing cold emails with AI:

  1. AI doesn’t know what you know.

    Whether you realize it or not, you possess a trove of tacit knowledge about your product/service and your prospects, and you tap into it whenever writing your messaging.

AI doesn’t even know the trove exists. It “knows” a lot thanks to its training, but it doesn’t have an understanding of your business. And unless you provide it with that crucial context, its output will be mediocre.

  1. AI isn’t good at doing two things at the same time.

    There’s a reason why many cold email tools offer a similar workflow: you add recipients, then create copy and personalize.

It’s because these steps naturally flow from each other. You first need to know who you’re contacting, and only then can you create relevant messaging.

When you ask AI to do everything at once, you disrupt that flow, and email relevance gets lost in translation.

You can address both problems by providing contextual information and by breaking down the copywriting process into several steps. Here’s how.

Document key context

Just like you, AI needs to understand who your recipients are, what they care about, and how you can help them.

Document these in great detail:

  • Who your ideal customer is
  • What problems you’re addressing
  • What the solution you’re offering is
  • Your unique value proposition

Use a step-by-step prompting workflow

We have tried dozens of approaches to prompting for cold-email copywriting, and we’ve tested many existing solutions. We’ve realized that bad results come from the fact that you don’t provide enough information, and that you’re trying to do everything at once. An ideal approach that we implemented in our AI writing assistant is to break down the process into two main steps:

  1. You give AI your broad ICP information, and as much context about the problem/solution as possible, in order to create an email template that is not personalized but highly relevant for everyone in the audience.
  2. You use AI to personalize every email, using the available data points about every recipient to reshape the template created at the previous step.

Template prompt

You are a world-class BDR, and you're doing your best work. Create a cold email.

ICP: {insert your ICP}

Problem I’m solving: {describe your ICP’s most urgent problem that you’re solving (not your solution—just the problem)}

My solution: {describe your solution with maximum fidelity. Include pricing details, full set of features, value propositions}

My unique selling proposition: {describe the main reason why the recipient should consider your solution}

Campaign goal: {e.g. “get a reply that confirms interest in a free trial}

Email length: {e.g. 100 words}

Always use sentence case for the subject lines. Focus the subject line on the problem I’m addressing in a way that generates curiosity. Write a cold email that’s focused on a relevant problem or need, hyperspecific to the recipient based on the ICP.

Personalization prompt

You are a world-class BDR, and you're doing your best work. Create a personalized cold email by contextualizing the template I provide to make it maximally relevant to the specific recipient.

Contextualization prompt

ICP: {insert your ICP} Problem I’m solving: {describe your ICP’s most urgent problem that you’re solving (not your solution—just the problem)} My solution: {describe your solution with maximum fidelity. Include pricing details, full set of features, value propositions} My unique selling proposition: {describe the main reason why the recipient should consider your solution} Campaign goal: {e.g. “get a reply that confirms interest in a free trial} Email: {insert the AI template} Recipient: {insert recipient attributes}

Figure out what your prospects want

To be relevant, you need to know what your recipients care about and how your product or service helps.

AI can help you:

  • Challenge your assumptions about your ideal customer’s pains and gains.
  • Narrow down your value props for subsegments of your market.

Pains & Gains prompt

List the top pains and desired gains (as in the Value Proposition Canvas) for a VP of RevOps at a 200-person SaaS company. Rank each pain/gain on a 1–5 scale based on how pressing and how common it is.

Figure out the best person to contact

If you have multiple contacts at a single company, it’s often a good idea to contact several of them… But not at the same time. Start by selecting the single best person to contact.

AI can help. If it’s a single company that you’re struggling to figure out, use this prompt:

Choose The Recipient prompt

I want to send a cold email to a company in {describe industry} and my offer is {describe the relevance of your message}. Which of these contacts should I reach out to: {paste job titles}.

Create synthetic recipients and ask AI for their reactions to the emails you send.

Here’s my email sequence: {paste your emails here}. I want to send this to {describe your audience}. Create ten different synthetic recipients that fit this category, and predict their reactions to receiving these emails in a way that helps me improve my copy and messaging for maximum relevance.

Create follow-ups that add value

For most cold email campaigns, following up is a surefire way to get more replies.

AI can draft entire email sequences to give you ideas for how to reengage your recipients with consecutive messages.

Value Added Sequence prompt

Write 2 follow-up emails that I'll send in the same email thread. In the first email, focus on addressing the most likely objection to the first email. Don't assume the first email was read. Very briefly reference the content of the first email by reiterating the main offer. In the second email, ask an open question about how the problem is currently being addressed by the recipient.

Figure out a goal for your campaign

Before you let AI loose on copywriting, decide exactly what the sequence should accomplish. Using AI, you can create quick previews of the same email with varying CTAs, and anticipate how your recipients will react.

CTA Brainstorm prompt

I’ll give you a cold-outreach email. Your job is to:

  1. Read the email and identify where the call to action (CTA) is or should be placed.
  2. Generate {X} alternative CTAs (number them CTA #1 … CTA #{X}). Each should be ≤ 20 words and align with the email’s tone, audience, and offer.
  3. Output a markdown table with these columns:
    • CTA (verbatim text)
    • Pros for the sender (max 2 bullet points)
    • Cons for the sender (max 2 bullet points)

Change the tone of voice

Tone of voice represents subtle, yet significant, changes in your messaging. AI makes it painless to create voice variants that are wildly different from your typical voice.

Tone of Voice prompt

Rewrite the email below and make it sound like Stellan Skarsgaard's character in Andor.

Turn an email into a LinkedIn DM/voice message script

Cold outreach doesn’t live in the inbox alone. Repurposing your email for social or voice keeps messaging consistent while meeting prospects where they already spend time.

Data Sourcing prompt

For a campaign targeting Heads of Customer Success at B2B SaaS firms, list the five best publicly available data points I can reference (e.g. open job posts, product-review scores). For each, recommend a free or low-cost source and tell me how to capture it at scale.

Wrapping up

I used to be sceptical about AI when it first saw it impact my inbox, and I was wrong. The question isn’t if, but how we should use LLMs to make the job of connecting with our prospects easier.