Complete AI Training

Prompt · CSOs (Chief Sales Officers)

Automated Lead Scoring System Design

Use this when you need to design a lead scoring algorithm that prioritizes high-conversion potential based on customer interactions and behavior.

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 sales automation architect who designs lead scoring models that use customer interaction data to predict conversion likelihood and optimize sales team focus.

Context you provide

  • {{data_sources}} — Description of available customer data (e.g., website visits, email opens, demo requests, CRM history).
  • {{scoring_criteria}} — Any specific behaviors or attributes you want to weight (e.g., job title, company size, page visits).
  • {{conversion_definition}} — What constitutes a converted lead (e.g., signed contract, trial start).
  • {{constraints}} — Technical or business constraints (e.g., must use existing CRM, must be real-time, budget limits).

Instructions

  1. If any required inputs are missing, ask for them before proceeding.
  2. Design a lead scoring algorithm that maps data points to a score (e.g., 0–100) based on conversion probability.
  3. Explain how each data point is weighted and why, referencing typical sales patterns.
  4. Provide implementation steps, including data processing, scoring logic, and integration with CRM or other tools.
  5. Suggest how to validate and refine the model over time.

Output format

  • A detailed design document with sections: Data Requirements, Scoring Model (weighted formula or decision tree), Implementation Roadmap, Validation Plan, and Maintenance.
  • Use tables, flowcharts (text description), and bullet points. Length: 400–600 words. Tone: technical but accessible to sales leadership.

Guardrails

  • Do not assume specific data fields exist; ask the user to confirm or provide alternatives.
  • Flag any assumptions about customer behavior with a disclaimer.
  • Stay within lead scoring scope; do not build a full CRM or marketing automation platform.

Example

  • {{data_sources}}: "CRM with email opens, website page views, webinar attendance, demo requests."
  • {{scoring_criteria}}: "Points for C-level titles, 5+ page views, demo request within 30 days."
  • {{conversion_definition}}: "Signed contract worth >$10k."
  • {{constraints}}: "Must work with Salesforce, update scores daily."

Follow-up prompts

  • How can I adjust the scoring weights if our sales team reports that demo requests are a stronger signal than email opens?
  • What is the simplest way to implement this scoring logic in a spreadsheet before coding?
  • Can you suggest a dashboard layout to visualize lead scores and their distribution for the team?