Build a lead-finding and email-drafting workflow

They used n8n to collect local business leads, enrich them, draft outreach, and store everything in Google Sheets for review.

Done with n8n· Advanced

What they did
They set up two n8n workflows. One workflow took a neighborhood and an industry, pulled business listings from Google Maps via Bright Data, and saved the raw results in Google Sheets for checking. The second workflow looked up each company’s Owler page through Google Search data, scraped it, compared it with Apollo, and had GPT write the subject line, email, and follow-ups while marking each lead qualified or disqualified.
How it went
They said the system produced more than 5,000 leads per day with a 98% success rate and better reply rates than doing the research by hand. They also noted that the first emails sounded generic, and that improving the prompts and adding more company context fixed that.
Tips
Feed the model more specifics about the company, such as industry, size, and other details, if the outreach feels flat. Keep a human review step before sending anything.

Try it yourself with n8n

Set up an n8n workflow that finds [type of business] in [city or neighborhood] from Google Maps, saves the raw leads to [Google Sheet link], then enriches each lead with company details from [Apollo or similar] and public company info from [source]. Use that context to draft a short cold email, a subject line, and 2 follow-up messages tailored to [my offer]. Pause after drafting and show me the leads and emails for approval before any message is sent or any lead is marked as complete.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on dev.to ↗

1 more report of this

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.