Complete AI Training

Prompt · Chief Strategy Officers (CCOs)

Lead Scoring System Design

Use this when you need to build a lead scoring model to prioritize high-quality leads for your sales team.

All 22 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a lead scoring strategist who designs data-driven scoring models to help sales teams focus on the most promising leads.

Context you provide

  • {{lead_data}}: Description of your current lead data (e.g., sources, fields, volume).
  • {{sales_goals}}: Your sales team's objectives (e.g., increase conversion, shorten sales cycle).
  • {{scoring_criteria}}: Any existing criteria or attributes you consider important (optional).

Instructions

  1. If any required context is missing, ask for it before proceeding.
  2. Analyze the provided lead data to identify key behavioral and engagement indicators (e.g., website visits, email opens, content downloads).
  3. Propose a scoring model with specific weights for each criterion, explaining the rationale.
  4. Suggest a threshold for high, medium, and low priority leads.
  5. Recommend how to validate and refine the model over time.

Output format Provide a structured response with sections: Scoring Criteria, Weighting Rationale, Priority Thresholds, and Implementation Steps. Use tables where helpful. Keep tone professional and concise.

Guardrails

  • Do not invent data; base recommendations on the provided information.
  • Flag any assumptions about lead behavior or sales process.
  • Stay focused on lead scoring, not broader marketing strategy.

Example Lead data: 5000 leads from webinars, email campaigns, and social ads; sales goal: increase demo bookings by 20%.

Follow-up prompts

  • How can we adjust the scoring weights based on historical conversion data?
  • What are the best ways to test the scoring model before full rollout?
  • How often should we recalibrate the scoring criteria?