n8n orchestrates, LangGraph writes, a human approves: an AI cold-email pipeline that can't spam

Описание и применение

Пайплайн для холодных писем на основе n8n и LangGraph, где каждый утверждение подтверждается данными, проверяется кодом и отправляется только после ручного одобрения, предотвращая спам и нарушения домена.

Задача

AI SDR demos often send many unverified emails, damaging domains and containing unsupported claims.

Результат

The pipeline achieved 26/26 checks in tests, processed 10 fake leads with 6 drafts awaiting approval, 2 disqualified, 1 deduped, and 1 blocked by unsubscribe list, demonstrating reliable, spam‑free cold‑email generation.

Рабочий процесс

• Trigger email generation (manual, schedule, webhook)
• Use Apollo to find prospects and enrich emails
• Verify emails with Hunter
• Deduplicate against CRM (HubSpot or Google Sheet)
• Apply qualification filters
• Generate research note via LangGraph
• Draft email from research note via LangGraph
• Run code‑based checker to validate claims, numbers, placeholders, unsubscribe line, and length
• If draft fails, rewrite up to two times
• Flag draft as needs_human_fix after two failures
• Create approval link per draft
• Send email via SendGrid (or Gmail/SMTP) behind SEND_ENABLED flag

Доказательства

Every claim in an email must come from sourced data, quoted from what the APIs returned.

Источник

A rule checker rejects bad drafts and sends them back for a rewrite (max 2 times).

Источник

Nothing is sent until a human clicks Approve.

Источник

21 pytest tests for the LangGraph service, 8 JS tests for the n8n Code nodes

Источник

10 fake leads end to end: 6 drafts waiting for approval, 2 disqualified, 1 deduplicated, 1 blocked by the unsubscribe list

Источник