As of 13 August 2026, AI can only partly rank the leads in your CRM.

What to actually do

1. Hand it to a person

   The route this page recommends

   A person who owns the outcome does this end to end, worth it when the failure is dear.

2. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   A chat interface, power-user skill, and roughly 30 minutes until you can act on the result.

   How to actually do it

   1. Open your CRM and export the relevant lead records, including lead ID, company, role, sector, location, source, contact history, engagement dates, stated need, qualification fields and current status.
   2. Remove unnecessary personal data and replace names or contact details with lead IDs before pasting the export into a chatbot.
   3. Write down your target customer definition, disqualifying conditions, buying signals and the number of leads your team can follow up within the relevant period.
   4. Paste the prompt and the cleaned CRM export into the chatbot, replacing each bracketed section with your sales rules and product description.
   5. Check every high-ranked lead against the original CRM record and move any lead with missing, stale or contradictory evidence into the review-needed group.
   6. Ask a sales colleague to challenge the criteria and inspect a sample of the rankings, then copy the agreed priority list and next actions back into the CRM.

   Prompt

   Rank the leads in the CRM data below for sales follow-up.
   
   Use these criteria, in this order:
   1. Evidence of a current problem that our product can solve: [describe the evidence]
   2. Fit with our target customer: [describe company size, sector, location and role]
   3. Buying intent or urgency: [describe the signals]
   4. Ability to buy: [describe the relevant budget, authority or account signals]
   5. Recency of engagement: [describe which activities matter and how recently]
   
   Our product or service: [describe it briefly]
   Our disqualifying conditions: [list them]
   Our sales capacity or follow-up limit: [state how many leads can be contacted and over what period]
   
   Rules:
   - Use only the information in the CRM data and the criteria above.
   - Do not infer budget, authority, need, identity or intent from a name, job title, postcode, ethnicity, gender or other proxy.
   - Do not invent missing facts. Mark missing or conflicting fields clearly.
   - Give each lead a priority score from 0 to 100, but do not present the score as a probability of conversion.
   - Show the main evidence for the score, the missing information, any disqualifying issue and the next sensible human check.
   - Put leads with insufficient evidence into a separate review-needed group rather than guessing.
   - Return a table with: rank, lead ID, priority score, evidence, missing information, risk or disqualifier, and next action.
   - Then explain the scoring rules in plain English and list any records whose ranking could change if one missing fact were supplied.
   
   CRM data:
   [paste the exported CRM data here]

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.