AI for GTM · Take this with you

Four prompts your team can run tomorrow.

These are the working prompts behind the four build-alongs in the AI for GTM course. Nothing here is a demo. Paste them into whichever assistant your company already gave you, point them at your real accounts, and keep the ones that earn their place. Share this page with your team.

1Pick your lane below. Every prompt has a variant for how you actually sell.
2Start with the daily brief. It is the one that changes your morning.
3Use real accounts. A prompt run on a made-up company teaches you nothing.
4Save what works as a Project instruction or a Skill, so you never write it twice.

Your lane

Your daily brief

A morning routine that tells you who to reach out to, what changed, and the three actions that matter today. Save it as a Project instruction and run it every morning.

Save as a Project instruction, run each morning

You are my AI GTM teammate. Each morning, build my daily brief from my connected sources (CRM, calendar, email, call recordings) plus any notes I paste. Output:

1. What changed in the last 24 hours across my accounts and open deals.
2. Who I should reach out to today and why, with the single best reason to engage each one.
3. My top three actions for today, ranked, each tied to a SPICED element or a Bowtie stage.
4. One risk I am ignoring.

Keep it to one screen. Never invent facts; if a source is missing, say so and tell me how to find it.

Your laneFocus on open opportunities, stalled deals, and the next action that moves each toward its Critical Event.

You leave with: A daily brief running against your real book of business.

Research while you sleep

An overnight deep-research report on a target account, plus a five-minute brief you run right before any call. The first one runs while you are asleep. The second takes less time than finding the meeting link.

Overnight deep research, run before you log off

Run deep research on [COMPANY] so I can prepare for a major pitch. Use connected sources plus public information. Deliver:

1. Company snapshot: size, segment, what they sell, recent news and stated priorities from earnings or filings.
2. Why now: triggers and events in the last 90 days that create a reason to engage.
3. Stakeholder map: likely buying-committee roles and who to multi-thread.
4. Bowtie read: where this account likely sits (net-new, onboarding, adoption, expansion).
5. Three points of view connecting their stated priorities to our value.
6. A first-touch message draft.

Cite where each claim comes from and flag anything you could not verify.

Five-minute pre-call brief

I have a call with [CONTACT, ROLE] at [ACCOUNT] in a few minutes. In under one page: what I need to know about the client, what they should know about us, the one outcome to drive in this call, and the two best opening questions. Keep it decision-oriented.

Your laneAim the pre-call brief at an active opportunity and emphasize the next SPICED gap to close on the call.

You leave with: An overnight report on a live target plus a repeatable pre-call brief.

Run the call, prove the impact

AI in the loop on a real, active opportunity. One prompt before the call to plan discovery, one after to score whether you actually uncovered quantified Impact and a dated Critical Event.

Before the call: the discovery plan

I have a discovery call with [CONTACT, ROLE] at [ACCOUNT] on [DATE]. Generate a SPICED-structured discovery plan. For each of Situation, Pain, Impact, Critical Event, and Decision, give me two to three sharp open questions tailored to what we know, plus the one piece of evidence I should listen for to mark it Qualified. End with the top three risks to this deal and how to probe them.

After the call: the scorecard

Here are the notes or transcript from my discovery call: [PASTE]. Score it against SPICED. For each element output Qualified, Partial, or Gap, the evidence from the call, and the exact follow-up question to close any gap. Pay special attention to whether Impact was quantified and whether a Critical Event with a date surfaced. Then give me a clean SPICED summary I can paste into CRM and the recommended next step.

Your laneRun the full before-and-after loop on a live deal. This is the core lane for this workflow.

You leave with: A discovery plan for a live opportunity plus a scored gap list.

Turn the workflow into a Skill

Take the call you just ran, turn it into the asset, then save the whole workflow as a reusable Skill so you never write the prompt again. This is the one that compounds.

Call to asset

Here is my discovery call transcript or SPICED summary: [PASTE]. Turn it into a [proposal / demo deck outline]. Lead with the customer's quantified Impact and Critical Event, then our recommendation, then the plan and the ask. Give me a clean storyline and slide-by-slide content I can drop into a deck.

Save it as a Skill

I want to turn the workflow I just used into a reusable Skill I can run on demand. Here is how I did it: [DESCRIBE]. Write it as a clear, repeatable Skill: the trigger, the inputs it needs, the steps it runs, the connected sources it pulls from, the output format, and the guardrails so it never invents facts. Then show me the final Skill text to save.

Your laneBuild the Skill around the proposal or business-case generator.

You leave with: A proposal or deck plus one working personal Skill.

Put this line on every prompt

Never invent facts. If a source is missing, say so and tell me how to find it. Keep outputs concise and decision-oriented.

Assistants guess when they are missing something. This line makes them tell you instead. It is the cheapest quality control you will ever add.

These prompts run in Claude, ChatGPT, Copilot, or Gemini. The daily brief and the overnight research get much better when your assistant is connected to your CRM, calendar, and call recordings, so start there if you have it. Check your own policy before pasting customer data into any assistant.

Go deeper

The AI for GTM Certification Course

Having the prompt is the easy part. Each of these returns more than you can use, and the judgment call is which three things to keep and what to do when the output is confidently wrong. That is what the course drills, live, on your own deals, with feedback on what you actually produced.

Four sessions of build-alongs. You leave each one holding a working artifact, and you finish certified, holding a Skill your whole team can run.

See the course

Winning by Design AI for GTM · Prompt library