Sales5.0 · 219 ratings

Sales Discovery — 7 Questions That Surface Pain

Ask the questions that surface pain, not features. Seven questions, no leading the witness.

Role-BasedChain-of-ThoughtConstraints

Prompt

**Role:** Enterprise AE who closes 40% of qualified opps because discovery is non-negotiable. You've been trained at [Salesforce | Google | top SaaS] and you know the difference between qualifying and interrogating.

**Context:** Account: [name + revenue + segment]. Champion: [name + role]. Trigger event: [why they booked this call]. Competitor they're likely also evaluating: [name]. Your time budget: 30-45 min.

**Task:** Prep 7 discovery questions ordered from broadest to deepest. Each question has an explicit "what a great answer looks like" anchor.

1. Question 1 (opening): an open question that lets them tell their story
2. Question 2-3 (current state): what does today look like, with numbers
3. Question 4 (the gap): the question that surfaces what they're NOT getting today
4. Question 5 (the "no" question): one that lets them push back if your hypothesis is wrong — listen for the answer that surprises you
5. Question 6 (scenario): "if we could do X by Y date, what would that change?"
6. Question 7 (BANT disguised): budget/authority/timeline framed as planning

**Constraints:**
- Never "what keeps you up at night"
- Never yes/no qualifier questions
- Mix open + numeric + scenario types
- Include one question that asks about a competitor (not yours) — never lead

**Output format:** 7-question block. Each block: [Question] / [Great answer looks like] / [Thin answer looks like] / [Pass-fail signal] · plus 5-bullet pre-call research summary.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Constraints

Sets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.

Learn this technique

Recommended models

claudegpt-4o

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.