How to Analyze CRM Data for Growth With Claude

Your CRM tells you who bought. LeadOcean tells you how many more like them exist. Connect https://api.leadocean.io/mcp first (setup is on the MCP page) and paste the prompt below.

The prompt

Here are my closed-won accounts from the last 12 months (CSV: company, industry, employees, country, deal size).
1. Find the pattern: which industry, headcount band and country hold most of the revenue?
2. Call leadocean_list_enum_values for industry and employeeRange and map the winning segment to exact values.
3. Call leadocean_count_leads for VP Sales buyers in that segment.
4. Tell me the count and the filters you used.
5. Do not call leadocean_search_leads until I say go.

Dirty rows skew the pattern, so clean the export first. The CRM data hygiene guide shows how.

What it resolves to

This is the segment from a sample pattern: US software companies with 51 to 500 staff. Your CRM may point somewhere else, and Claude will map it the same way.

How many match

2,752 mailable people matched on 1 October 2026. Filters: jobLevel VP, jobFunction Sales & Business Development, industry Software Development or Computer Software, employeeRange 51-200 or 201-500, country US.

Mailable means verified, catch_all_valid or catch_all, the count_leads default. The count is free. Of the 2,752, 1,652 sit at companies with 51-200 employees.

Read the count against your closed-won list. If you have won 40 accounts in a segment that still holds 2,752 buyers, that segment has room. If the count is small, widen one filter at a time and count again.

What you get back

Search rows carry the fields below. These are placeholder values, not real records.

Variations

• Ask Claude to rank your segments by closed-won count and count the top three separately.
• Swap the buyer line for "Directors of Marketing, jobLevel Director" to size a second persona.
• Add "country GB" and compare the two counts before you pick a market.

Records it spends

The enum lookups and the count are free. leadocean_search_leads costs 1 record per person returned, so a limit of 25 costs 25 records. Free gives you 1,000 records one-off with no card. Pro is $499 a month. See pricing.

Related prompts

• Enrich data
• Use technographic data
• Turn closed-won deals into an ICP

More prompts live in the prompts hub.