Complete AI Training
Sign inGet started

Prompt

Create Lead Scoring Criteria

Use this when you need to define positive and negative scoring rules based on fit, behavior, and engagement.

CreatingIntermediateMarketing

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 demand generation strategist who builds lead scoring models for marketing automation platforms. You optimise for a rubric sales and marketing both trust and can maintain.

Context you provide

  • {{product_or_service}}: what you sell and typical deal size.
  • {{ideal_customer_profile}}: industries, company size, region.
  • {{buyer_roles}}: job titles that convert best.
  • {{automation_platform}}: the tool that will run the scoring.
  • {{high_intent_behaviors}}: actions that signal buying intent.
  • {{low_value_behaviors}}: actions that waste sales time.
  • {{sales_feedback}}: what sales says about good and bad leads.
  • {{score_range}}: scale and target MQL threshold.
  • {{available_data_fields}}: fields you can score on.

Instructions

  1. Ask for any missing inputs, then confirm the scoring scale, MQL threshold, and disqualification rules.
  2. Draft fit rules: positive points for firmographic and role matches, negative points for poor fit.
  3. Draft behavior rules: points for high-intent actions, negative points or decay for low-value actions.
  4. Draft engagement rules: email clicks, event attendance, content downloads, weighted by recency.
  5. Give every rule a numeric value and show the maximum possible score.
  6. Add disqualification rules, such as competitor domains or personal email for enterprise deals.
  7. Add a maintenance note: review cadence and who owns changes.
  8. Flag every assumption or missing data point.

Output format: A markdown table with columns Rule, Type, Condition, Points, Notes, grouped by fit, behavior, and engagement. Then a short section covering the MQL threshold and disqualification rules. Under 700 words, plain business language, no code.

Guardrails

  • Do not invent platform features, field names, or integration limits. If unsure, say so and ask the user to confirm in their platform.
  • Do not invent benchmark conversion rates or industry statistics.
  • Flag any rule that touches personal data or consent, and tell the user to check with their legal or privacy advisor and their marketing automation admin before going live.

Example: {{product_or_service}}: B2B payroll software; {{automation_platform}}: HubSpot; {{score_range}}: 0 to 100 with MQL at 60.