As of 13 August 2026, AI can only partly classify leads by company size.

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, chat-fluent skill, and roughly 30 minutes until you can act on the result.

   How to actually do it

   1. Open your CRM or spreadsheet and export the lead name, legal or trading company name, website domain and any existing employee-count, turnover or company-size fields.
   2. Write down the company-size bands you actually use, including the measure and threshold for each band, and paste them into the prompt.
   3. Remove irrelevant personal data, then paste the lead data and any source links or dated enrichment records into the prompt.
   4. Ask the model to classify the list using the supplied prompt, and save its table with the evidence, confidence and review reasons.
   5. Open the cited company records and compare the employee or turnover evidence for every high-value lead and every low-confidence or contradictory lead.
   6. Change unsupported classifications to unknown or human review, then send only the checked size field and its source into the CRM.

   Prompt

   Classify the following leads by company size for UK B2B sales.
   
   Use these size bands exactly: [insert size bands, such as micro, small, medium and large, with the employee or revenue thresholds you want].
   
   Use only the information supplied below or clearly identified public sources. Do not invent employee counts, revenue, group structure or parent-company details. Do not treat turnover as employee count, or employee count as turnover, unless I explicitly tell you to use that proxy. If the evidence is missing, contradictory or out of date, mark the lead as unknown or needing review rather than guessing.
   
   For each lead, return a table with:
   1. Lead name
   2. Company name
   3. Assigned size band
   4. Size measure used, such as employees, turnover or another stated measure
   5. Evidence supporting the classification
   6. Source and source date, if supplied
   7. Confidence: high, medium or low
   8. Reason for any uncertainty
   9. Recommended action: accept, reject or human review
   
   After the table, list all leads needing human review and explain the specific missing or conflicting evidence. Keep the classification separate from any judgement about sales fit.
   
   Lead data:
   [ paste lead names, company names, domains, CRM fields and any company-size evidence here ]

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