SalesSaves about 30 minutes per meetingTested on Claude Sonnet 5.5 and GPT-6, Nov 2026

Prepare a one-page account brief before a sales meeting

What this does

This playbook turns the material you already have on a prospect into a one-page brief before a sales meeting. You paste website text, LinkedIn about text, past emails and CRM notes. You get what the company does, likely priorities, three questions to ask, risks, what to avoid and a clear list of unknowns. A person still checks it before the call.

Fill in your detailsDownload skill
On this page

Before and after

Before

  • The rep skims the company website, scrolls the LinkedIn profile and searches the inbox for old emails minutes before the call.
  • Notes sit in different places, and the questions come out generic.
  • Gaps in knowledge only show up during the meeting.

After

  • The rep pastes the same sources into one prompt and gets a one-page brief with priorities, three questions, risks and a list of unknowns.
  • They check it against the sources and walk in knowing what they do not yet know.

Saves about 30 minutes per meeting

From my practice

The briefs that help are the ones that admit gaps. A rep who walks in knowing what is unknown asks better questions than one holding a confident guess. I suggest reading the brief once, crossing out anything you cannot trace to your own notes, and adding one thing you know that the AI could not.
· AI workflow and adoption consultant

What to have ready

  • The company's website text: the About page, a services or products page and any recent news page, pasted as plain text.
  • The contact's LinkedIn about text and current job title, copied from their public profile.
  • Any past emails or messages with this company, with personal phone numbers and addresses removedKeep the date on each one.
  • Your CRM notes: how the lead arrived, who you have spoken to and anything agreed.
  • A line on the meeting: date, length, what you sell and what you want from the call.

Build your prompt

  1. 1. Gather your inputsHave the items above to hand.
  2. 2. Fill in the formYour prompt updates as you type.
  3. 3. Copy or open in your AIClaude, ChatGPT or Gemini.
  4. 4. Review before you sendCheck it against your notes.
Fill in your details

Fill these in. Your prompt updates as you type, and stays in this browser tab.

Your prompt · 0 of 7 filled

I am a sales rep preparing for a meeting. Write a one-page pre-meeting brief using only the material I paste below. Do not use outside knowledge about the company and do not guess. If something is not in the material, write "Unknown" and say what I could ask or check to find out. Company: The company you are meeting Contact: The contact's name and job title About the meeting and what we sell: Date, length, what you sell and what you want from the meeting Company website text: Text copied from the company's website (About, services, news) Contact's LinkedIn about text: The contact's public LinkedIn about text Past emails with them: Past emails or messages with the contact, personal details removed CRM notes: Your CRM notes on this lead Write the brief with these headings: 1. What they do: two or three plain sentences. 2. About the contact: role, what they appear to care about, and how they write (formal, brief, detailed). 3. Likely priorities: up to four. Label each "Stated" if the material says it, or "Inferred" if it is your reasoning from the material, with a short reason. 4. Three questions to ask: open questions that fit the meeting goal and cannot be answered from the material. Add one line on why each is worth asking. 5. Risks: up to four, such as a supplier already in place, budget or timing signals, a stalled earlier conversation, or a different decision maker. 6. What to avoid: topics, claims or wording to steer clear of, based on the material. 7. Unknowns: what the material does not tell us that matters for this meeting. Rules: Keep it to one page, about 350 words, in short lines I can read on a phone just before the call. If the sources disagree, show both and say which is more recent when dates are given. Do not invent names, numbers, customers or news. Leave out personal details about the contact that have nothing to do with their work. At the end, list every assumption you made.
Open in
Open in Claude (opens in a new tab)Open in ChatGPT (opens in a new tab)

Gemini cannot be filled from a link, so the prompt is copied first. Paste it with Ctrl+V or Cmd+V.

Use it as a skill

Add this playbook to your assistant once, then ask for it by name.

Download skill for ClaudeView SKILL.md (opens in a new tab)
How to install
  1. Claude: download the zip and upload it as is under Settings, Capabilities, Skills.
  2. Other assistants: open SKILL.md, copy it, and paste it into the assistant's custom instructions or project.
  3. Ask for the playbook by its task, and give it your details when it asks.

The skill is plain text with no scripts, links or commands. Read SKILL.md before you install it, and use a company-approved AI workspace. Need help setting it up? Book a call.

See a real result

Sample input: Kaveri Cold Chain Pvt Ltd, Pune · Rohan Deshmukh, Head of Operations · First 30-minute video call on Tuesday 18 November. We sell…

Sample output from Claude Sonnet 5.5, run 14 Nov 2026
Pre-meeting brief: Kaveri Cold Chain

Tue 18 Nov, 30 min video call. Contact: Rohan Deshmukh

1. What they do

  • Pune-based temperature-controlled transport.
  • Moves dairy, frozen food and pharma in Maharashtra, Gujarat and Karnataka using reefer trucks.
  • Website says real-time temperature monitoring is now on all routes.

2. About the contact

  • Head of Operations: runs dispatch, fleet and customer delivery commitments.
  • Cares about reducing delays and keeping customers informed.
  • Writes briefly and directly. Asked us to "keep it short."

3. Likely priorities

  • Fewer "where is my truck" calls from dairy customers: Stated (his 9 Nov email).
  • Fewer delays, customers kept informed: Stated (LinkedIn).
  • Less manual status handling: Inferred. Meena said two people answer calls and WhatsApp by hand.
  • Dispatch capacity: Inferred. They are hiring dispatch coordinators, which may mean workload pressure.

4. Three questions

  1. "What happens today when a customer asks where their truck is?" It shows the process, volume and pain, and none of that is in the material.
  2. "What does your GPS vendor provide, and can customers see any of it?" It shows whether we overlap with or complement the vendor.
  3. "What would need to be true for you to try something new, and who else would be involved?" It surfaces success criteria and the decision maker.

5. Risks

  • Existing GPS vendor may offer, or add, customer updates.
  • Limited time and patience: he asked for brevity.
  • No budget discussed.
  • Decision maker unconfirmed.
  • Thin history: a webinar lead and one short chat with Meena.

6. What to avoid

  • Pitching TrackLine as a GPS replacement.
  • Guessing at their systems, volumes or customers beyond dairy.
  • Long demos or overrunning 30 minutes.
  • Quoting savings or numbers we can't source.
  • Assuming Rohan knows what Meena told us.

7. Unknowns

  • GPS vendor: ask Rohan, or check with Meena.
  • Call volume and which customers call: ask.
  • Budget and timing: ask.
  • Decision maker: ask.
  • What "your note" referred to: check our sent email.
  • Whether customers prefer WhatsApp or email: ask.

Assumptions

  • "Saw your note" refers to our outreach after the webinar.
  • Meena's comment is current (it is undated).
  • Rohan's style is judged from one email and a short bio.
  • Customers' calls go to Kaveri's own staff.
  • The sources do not conflict.

Was this playbook helpful?

Want this set up for your team?

I can fit this playbook into your CRM, helpdesk or inbox and train your team to use it.

Book a 30-minute review

Review before you send

Check the result

Watch out for

  • Guessing presented as fact. The model may fill gaps with plausible statements, especially in the risks and 'what to avoid' sections, which the prompt does not ask it to label. Check each of these lines against your sources before relying on it.

  • Thin assumptions lists. In testing, the models listed only some of their inferences. Treat the list as a starting point and add any Inferred item it leaves out.

  • Old material. A website page or LinkedIn profile can be out of date. Note the date of each source in your paste where you know it, and treat older emails with care.

  • Personal and customer data. Past emails and CRM notes often contain personal details. Use your company's approved AI workspace, paste only what the brief needs, and follow your own data rules under India's DPDP Act or GDPR. This is not legal advice.

  • Over-reading a LinkedIn profile. A short about section says little about what a person wants. Treat the contact summary as a starting point and listen on the call.

  • Confidential information. Leave internal pricing, discount limits and other companies' details out of the paste unless your policy allows it.

Tips for your industry

This playbook works for any business. These notes help you adapt it.

Reps often run several short discovery calls a week, so the brief helps most with the unknowns: current tools, who signs off and what a trial would need to prove. Paste any product usage or trial notes into the CRM field.

Questions people ask

Paste it and write 'Not available' in the other fields. The brief will have more unknowns and fewer priorities, which tells you where to spend your discovery time. A short, honest brief is more useful than a confident one built on guesses.

Last checked · Updated