FrameworkExecutive Messaging

AI Prompts for Sales: The Enterprise Prompt Playlist

Most AI prompts for sales ask for an email from thin context, which is how you get polished emails that say nothing. These 13 plays get the deal context straight and diagnose first, then draft.

By Nate Nasralla6 min read
The short answer

The best AI prompts for sales run as a sequence instead of one-off requests. Give the model real deal context (call notes, emails, and the business case), have it diagnose what's going on, make the call on what to do next yourself, and only then ask it to draft. The playlist below has 13 plays and 52 prompts to run that way.

On this page
    Questions answered

    Frequently asked questions

    What are the best AI prompts for sales?

    Sequences, more than single prompts. The ones that work in enterprise sales start from real deal context, ask the model to diagnose before it drafts, and leave the key decision to you. A play like Stuck Deal Diagnosis runs four prompts: break down the deal, generate hypotheses, find a move to test each one, and only then draft a message.

    Can ChatGPT or Claude use my CRM data with these prompts?

    Not on their own. Labels like @Deal and @Meeting are placeholders for context you paste in yourself, such as call notes, email threads, and CRM fields. Only share material your company has approved for the tool you’re using.

    How much deal context should you give AI?

    Enough for it to diagnose the deal, not just describe it: the recent emails, your call notes, the people involved and who’s gone quiet, the stage history, and any business case draft. The thinner the context, the more generic the output.

    Simplify complex sales: get the latest frameworks.

    Short, practical frameworks for executive messaging, business cases, multithreading, and sales enablement.

    © Nate Nasralla · Complex sales training & advisory

    Ask any AI tool to write a follow-up after a discovery call, or a multithreading email in the mid-funnel, and you'll get something like:

    "Thanks so much for your time today! It was great learning more about your priorities around operational efficiency, and I'm excited to explore how we can support your goals."

    Which is... meh. It's better than not sending a follow-up, but it won't move your deal an inch forward, because it sounds like what every LLM's trained to do: predict the most likely, average response.

    What it can't do is think at a higher, more abstract level about what's missing, what wasn't said in the transcript, and how specifically to reason through those gaps based on experience.

    What does a quality AI prompt in sales start with?

    The specific context of the deal: call notes or a transcript, the email thread, the CRM fields, your business case draft, and anything the buyer has shared with you. In the playlist, that material shows up as labels like @Deal, @Meeting, @Prospect, and @Account Plan.

    These plays come from Olli, the agent inside Fluint (the company I co-founded), where they're pre-built and run against a team's connected deals. You can also run them yourself by copying the prompts into whatever AI you use, and feeding in the context by hand. It works decent, it just takes more effort, and more editing of the outputs, but it'll be a much higher-quality outcome than doing the job without the specific phrasings in this doc.

    How is a prompt playlist different from a prompt list?

    Each entry is four prompts, run in order. In most of them, the draft comes after the preceding steps, like diagnosing a stuck deal, so by the time you ask for the email, the model has already clued into and focused on the problem and the gaps inside its context window. (A few plays, like Pre-Call Prep, never draft at all, because their job is research.)

    None of the plays stops to make you choose, though. So if you'd like, instead of pasting in the full prompt, you can pause in between steps yourself: read the diagnosis, decide what's true about the people involved, and then keep going. That's the step a model can't do for you, since you're the one who knows which hypothesis fits the champion who went quiet.

    What's in the playlist?

    Thirteen plays, in the order a deal moves through them, with the first prompt from each:

    Prospecting and early engagement

    Discovery and qualification

    Building consensus

    Demo and evaluation

    Business case and mid-funnel

    Account management

    What does one play look like, end to end?

    Here's Stuck Deal Diagnosis, all four prompts, with @Deal standing in for the context you paste in first (the last few emails, your call notes, the stage history, and who's gone quiet):

    1. Deal Breakdown. Based on @Deal, what's the current state of this deal and where did it stall? Look at the last few interactions and tell me what might be going on.
    2. Root Cause Hypotheses. Give me 3 hypotheses for why this deal is stuck. Be direct: consider whether it's priority, politics, missing stakeholder, weak business case, or something else.
    3. Re-Engagement Options. For each hypothesis, what's one move I could make to test it and get the deal moving again? Give me specific actions, not generic advice.
    4. Changed Direction. Draft a "changed direction?" message I can send if nothing else works, something respectful that creates urgency without being pushy. The goal is an honest and direct answer.

    The first two prompts give you a read on what's happening in the deal. The third gives you a test for each hypothesis, and that's where your pause goes: test what fits what you know about the people involved. (If the stall is about priority, that might mean finding the compelling event you never confirmed.) The message in prompt four is the last resort, for when the tests come back empty.

    What should you do, vs. let AI do?

    Let AI research the account, but decide for yourself what you believe is going on, and say it in your own words (the point of view guide walks through that). Let it fill in the numbers on a customer's revenue model, but then, trace the path from your product to their outcome yourself, the way a driver tree makes you structure your thinking.

    And, ask the model to tell you which parts of its answer came from your notes and which parts it inferred.

    "Wait, aren't you the guy who built an AI company for sales teams?"

    I am, and I have.

    Which is why I know the difference between the AI that builds you up, and the AI that starts to hollow you out.

    If you hand it the keys completely, letting it draft every email, deck, recap, and plan every account, it feels incredible for about a month. But when you stop putting in the reps yourself and thinking critically, you slowly become the average of whatever the model spits out.

    Running plays like these keeps you in the work: the model does the digging and the drafting, and you do the thinking on your live deals.

    So pick one stuck deal, gather its last few emails and your call notes, and run the Stuck Deal Diagnosis. When prompt four comes back, edit the message until it sounds like you, then ship it.