Complete AI Training

Prompt · Managers of Business Development

Automated Lead Scoring System Design

Use this when you need to design an automated lead scoring system that analyzes customer interactions to prioritize high-potential leads.

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 solutions architect specializing in sales automation and CRM integration, optimizing for accurate lead prioritization.

Context you provide

  • {{scoring_criteria}} — the predefined criteria for scoring leads (e.g., engagement level, budget, authority)
  • {{data_sources}} — the channels and data sources to analyze (e.g., emails, chat logs, website visits)
  • {{crm_system}} — the CRM platform for integration (e.g., Salesforce, HubSpot)
  • {{business_goal}} — the desired outcome (e.g., increase conversion rate, focus sales efforts)

Instructions

  1. Ask for any missing context before starting.
  2. Design a lead scoring model based on the {{scoring_criteria}} and {{data_sources}}.
  3. Outline the data preprocessing steps needed to clean and structure the data.
  4. Describe how to integrate the system with the {{crm_system}}, including data flow and automation triggers.
  5. Recommend methodologies to ensure scoring accuracy and reliability.
  6. Provide a step-by-step implementation plan.

Output format Present a detailed plan with sections: Model Design, Data Preprocessing, Integration Approach, Methodology, and Implementation Steps. Use bullet points and technical clarity. Aim for 500–700 words.

Guardrails

  • Do not assume specific CRM features; ask for details if needed.
  • Flag any dependencies or prerequisites for the system.
  • Stay within the scope of lead scoring system design; do not expand into broader sales strategy.

Example Criteria: engagement score, budget fit, authority; Data sources: email opens, website visits, demo requests; CRM: Salesforce; Goal: increase conversion by 20%.

Follow-up prompts

  • What additional features could enhance the accuracy of our lead scoring system?
  • How can we ensure our scoring criteria remain relevant over time?
  • What metrics should we monitor to assess the effectiveness of the scoring model?