How to Personalize Outbound With Career History Data (Using the LeadOcean API)

Sales personalization tools write the sentence. The sentence is only as good as the fact you hand them. This guide builds the fact layer: a list of prospects, each with one verifiable detail from their career.

TL;DR

• Search one segment, enrich each person, and keep one career fact per row. It takes about 30 minutes for 25 prospects.
• It spends about 50 LeadOcean records for 25 prospects: 25 from the search, 25 from the enrich calls. The Free plan has 1,000 records for life.
• Size the list first with the free count. Sizing spends nothing.

Prerequisites

• A LeadOcean API key in $LEADOCEAN_API_KEY. Free works: no card, every feature, 1,000 records.
• curl and jq.
• Any tool that takes a CSV and writes the email: a sequencer, a spreadsheet, or an LLM prompt. This guide stops at the data.

Step 1: Size the list for free

Count before you pull. A count spends no records, so run it as often as you like.

In Claude or any MCP client connected to https://api.leadocean.io/mcp, call leadocean_count_leads:

{
  "jobLevel": ["VP"],
  "jobFunction": ["Sales & Business Development"],
  "country": ["US"],
  "employeeRange": ["51-200"],
  "facets": false
}

On 2026-10-21 this returned 18,567 people with a verified, catch_all_valid or catch_all email, across 12,192 companies. Without any email condition the same filters match 60,456.

Enum values are exact strings. If a filter returns nothing, check the spelling with leadocean_list_enum_values.

Step 2: Pull a small segment

Search the segment with a limit of 25. The body is flat JSON and every filter is an array.

curl -s https://api.leadocean.io/v1/people/search \
  -H "x-api-key: $LEADOCEAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jobLevel": ["VP"],
    "jobFunction": ["Sales & Business Development"],
    "country": ["US"],
    "employeeRange": ["51-200"],
    "limit": 25
  }' | tee search.json | jq '.meta'

Each person returned costs one record. For more rows, pass the cursor from the previous page. One search pages to 10,000 rows, then meta.depthCapped is true. Narrow the filters instead of walking further.

Step 3: Enrich each person for career history

Search finds the person. Enrich returns the history. Enrich takes exactly one of linkedin_url, email, phone or person_id, so use the person_id each search row carries at meta.source_ids.person_id.

jq -r '.data[].meta.source_ids.person_id' search.json | while read id; do
  curl -s https://api.leadocean.io/v1/people/enrich \
    -H "x-api-key: $LEADOCEAN_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{\"person_id\": \"$id\", \"reveal_email\": true}" \
    > "enrich_$id.json"
  sleep 0.3
done

Enrich returns resume_data with past roles, education, certifications and awards, each when the person has them. An enrich that finds nobody is a 404 and costs nothing. The sleep keeps you under 5 requests a second on Free.

Step 4: Pick one fact per person

A good personalization line is one true, checkable detail: a previous employer, a title change, a school. Each past role carries a title, company name, start and end dates and job level, when held (enrich docs, October 2026). Print a few entries and read the keys before you map them to CSV columns.

for f in enrich_*.json; do
  jq -c '.data | {
    now: .contact_data.contact_current_experiences[0],
    before: .resume_data.experiences[0:2]
  }' "$f"
done

Rules that keep the line honest:

• Use a past employer only if the dates are present.
• Skip anyone with an empty experiences list. Do not guess.
• One fact per email. Two reads as a dossier.

Step 5: Hand the fact to your writing tool

Write the CSV with email, first_name, fact and source_field. Then give your tool a prompt that cannot invent.

Write a 2-sentence opening for a cold email to {first_name}.
Use only this fact: {fact}
Do not mention anything not in the fact. No flattery. No questions.

Check contact_data.email_status before you send. LeadOcean does not refund bounces.

What you get

The count in Step 1, run on 2026-10-21, returned:

{
  "total": 18567,
  "totalIsExact": true,
  "totalAll": 60456,
  "distinctCompanies": 12192,
  "unsupportedFilters": []
}

Total is the mailable audience. The enrich response shape from the API reference, with placeholder values:

{
  "success": true,
  "data": {
    "profile_data": { "profile_full_name": "Jane Doe", "profile_headline": "VP Sales at Acme" },
    "contact_data": {
      "email_status": "verified",
      "contact_current_experiences": [
        { "job_title": "VP Sales", "company_name": "Acme", "company_domain": "acme.com" }
      ]
    },
    "resume_data": { "experiences": [], "educations": [], "certifications": [] }
  },
  "meta": { "schema": "leadocean.person.v1" }
}

The arrays are empty in this placeholder. On a real record, experiences holds one object per past role. If you would rather not parse JSON, the export column picker has past_N_job_title, past_N_company_name, past_N_start_date and past_N_end_date, though bulk CSV export needs a paid plan.

Past employers carry no company_id yet, so match them by name.

Troubleshooting

FAQ