Run a scheduled n8n workflow that scrapes leads, checks their GitHub bio and sends GPT-4o-mini cold emails
A builder documents a 21-node n8n workflow that scrapes freelance developer leads, validates emails, looks up a GitHub bio, writes a personalised email with GPT-4o-mini and sends it with pauses between messages.
Evidence: The source shows its work: steps, screenshots, code or data you can inspect.
The business problem
Small outbound campaigns need personalised emails with at least one verifiable fact, without writing each one by hand.
What was tried
A webhook or Tuesday and Thursday 9am schedule starts a run. An Apify actor pulls 20 Apollo profiles filtered by title and location, duplicates are removed against a Google Sheet, and emails are validated with mails.so. A best-effort lookup uses the LinkedIn slug as a guessed GitHub username to fetch the bio. GPT-4o-mini writes a subject and body as strict JSON under constraints (banned phrases, one verifiable fact, length limits), and Gmail sends each message with a 45-second wait, logging to the sheet.
What was reported (not reported)
A run of 20 emails takes about 30 minutes and about $0.04 in API fees. No reply, bounce or deliverability results are reported, and the post only cites an industry benchmark of 0.7 to 1.5% replies.
Limitations
Opt-outs are not handled, so a prospect who replies STOP would still get later batches (a fix is planned). About 60% of prospects have no matching GitHub handle and get less specific emails. The author sells the workflow as a $39 template, gives no results from real campaigns, and the page does not show a year. Costs for Apollo, Apify, mails.so and sender infrastructure are not stated. Check email consent and anti-spam rules before using it.
What you need
n8n, Apify with an Apollo actor, mails.so, the GitHub API, an OpenAI key, Gmail and Google Sheets. Total costs are not given beyond the per-run API fee.
Sources
- DEV Community (bluefin ships) ↗ Firsthand write-up, publication date unknown
Source published: unknown. Last reviewed here: October 11, 2026. Spot a mistake? Tell us.
Tools in this workflow
- OpenAI API: Writes each email with GPT-4o-miniTry OpenAI API
- n8n: Runs the workflowTry n8n
- Apify: Scrapes lead dataTry Apify
Related workflows
Send a Monday business metrics email from Stripe, Notion and Sheets with Claude writing the narrative in n8n
A shared n8n template pulls last week's Stripe revenue, Notion deal pipeline and a Sheets row of support numbers, has Claude write a three-paragraph summary, and emails and posts it to Slack.
Research sponsors, build a sponsorship CRM and schedule checks with the Manus agent
A content creator used Manus to find companies advertising in AI newsletters, build a web-app CRM for YouTube sponsorships, and schedule recurring lead and trend checks.
Automate an agency's client onboarding, lead intake, follow-ups and inbox triage with self-hosted n8n
A solo automation engineer lists seven n8n workflows for agencies, from CRM-triggered onboarding to proposal reminders, with AI used for inbox triage and content repurposing drafts.
Build a document-grounded RAG support chatbot with LangChain, Qdrant and OpenAI for a 500-PDF client
An AI engineer describes a retrieval-augmented chatbot deployed for one client with over 500 PDFs, with the chunking and retrieval choices, and reports 94% answer accuracy against 61% for plain GPT-4.