n8n Auto-Generate Research-Backed Cold Email Icebreakers

Input: product brief + target role/location → scrape lead websites → GPT summarize → generate personalized multi-line icebreaker → Output: Google Sheets rows

Who

SDRs, growth operators, and agencies who need high-reply-rate cold outreach at scale

You get

Automatically scrape prospect websites, generate multi-line personalized icebreakers referencing site details, and append results to Google Sheets for review or outbound sequencing

You need

n8n · google-sheets

Steps

1. Configure form trigger and credentials

   After importing the template into n8n, set up the Details (form trigger) node: confirm the Outreach form title and 6 fields (About your Product, Designation, Location, Keywords, Your Name, Product URL) with their required status. Then configure Credentials for OpenAI API key, Google Sheets OAuth2, and Apify API token (or your alternative lead source).

2. Submit form and fetch leads

   Submit your product description, target designation, location, etc. via the form. The workflow automatically calls Leads Scraper1 (HTTP Request node, default Apify act) to retrieve a list of potential contacts. Only Websites & Emails1 (Filter node) drops rows missing website or email, letting only valid leads proceed.

3. Scrape websites and extract pages

   Scrape Home1 fetches each lead's company homepage; HTML1 extracts all <a> links from the page. Edit Fields1 (Set node) normalizes fields including company_website, email, first_name, last_name, headline, location, and phone_number. Loop Over Items1 processes leads in batches.

4. Filter links, deduplicate, and convert to Markdown

   Split Out1 flattens the links array into individual items; Filter1 keeps only relative paths starting with /. Code1 runs JavaScript to normalize links (handle relative paths, convert absolute URLs to pathname, strip trailing slashes). Remove Duplicate URLs1 deduplicates, then Limit1 caps at 3 links by default. Request web page for URL1 fetches each link, and Markdown1 converts HTML to Markdown for GPT processing.

   Execution prompt · Source text。Code1 node JS Code field for link normalization

   Copy prompt

   const items = $input.all();
   
   const updatedItems = items.map((item) => {
     const link = item?.json?.links;
   
     if (typeof link === "string") {
       // Case: starts with "/" → already relative
       if (link.startsWith("/")) {
         item.json.links = link;
       } 
       
       // Case: absolute URL (http or https)
       else if (link.startsWith("http://") || link.startsWith("https://")) {
         try {
           const url = new URL(link);
           let path = url.pathname;
   
           // Strip trailing slash unless root "/"
           if (path !== "/" && path.endsWith("/")) {
             path = path.slice(0, -1);
           }
   
           item.json.links = path || "/";
         } catch (e) {
           // On parse error, keep original
           item.json.links = link;
         }
       }
   
       // Fallback: not relative or absolute, leave as-is
       else {
         item.json.links = link;
       }
     }
   
     return item;
   });
   
   return updatedItems;

5. GPT summarize each page

   Summarize Website Page1 (OpenAI node, model gpt-4.1) receives Markdown page content and outputs a two-paragraph abstract. The system role is set as a website scraping assistant; the user prompt requests JSON output {"abstract":"..."} with a straightforward, spartan tone.

   Execution prompt · Source text。Summarize Website Page1 node system message

   Copy prompt

   You're a helpful, intelligent website scraping assistant.

   Execution prompt · Source text。Summarize Website Page1 node user message (summarization instruction)

   Copy prompt

   You're provided a Markdown scrape of a website page. Your task is to provide a two-paragraph abstract of what this page is about.
   
   Return in this JSON format:
   
   {"abstract":"your abstract goes here"}
   
   Rules:
   - Your extract should be comprehensive—similar level of detail as an abstract to a published paper.
   - Use a straightforward, spartan tone of voice.
   - If it's empty, just say "no content".

   Execution prompt · Source text。Summarize Website Page1 node user message (dynamic input variable)

   Copy prompt

   ={{ $json.data }}

6. Aggregate summaries and generate icebreaker

   Aggregate1 aggregates all page abstracts into an array. Generate Multiline Icebreaker1 (OpenAI node, model gpt-4.1, temperature=0.5) reads aggregated summaries, lead profile, and product description to generate a JSON-formatted complete cold email (subject + body). The system role is a sales assistant; the user prompt includes the email template structure, tone rules, and a full few-shot example (Maki Agency case).

   Execution prompt · Source text。Generate Multiline Icebreaker1 node system message

   Copy prompt

   You're a helpful, intelligent sales assistant.

   Execution prompt · Source text。Generate Multiline Icebreaker1 node user message (email generation instruction with template and rules)

   Copy prompt

   =We just scraped a series of web pages for a business called {companyName}. Your task is to take their summaries and turn them into personalized full cold email bodies that feel researched and tailored.
   
   You’ll return each email in the following format:
   
   {
     "email": "Subject: A quick idea for {companyShort}\n\nHi {name},\n\nI spent some time on {companyShort}’s site and noticed {specificThing}. It’s a small detail, but it shows how much you care about {valueTheyCareAbout}, which not everyone in {industry/space} prioritizes. I also saw the focus on {secondThing}, which signals a bigger strategy around {insight}.\n\nThe reason I’m reaching out: we built {productDescription}, a lightweight but powerful tool that costs just a few cents per run, scales easily, and consistently drives high conversion rates. A few things that set it apart:\n- {featureOne}\n- {featureTwo}\n- {featureThree}\n\nIf you’d like a closer look, I’ve shared a link here: {{ $('Details').item.json['Product URL'] }}. My sense is that {companyShort} values {someImpliedBeliefTheyHave}, and this tool aligns directly with that. Would you be open to a short conversation to see if it could fit into what you’re already running?\n\nBest regards,\n{{ $('Details').item.json['Your Name'] }}"
   }
   
   
   
   Rules:
   
   Keep the tone professional, concise, and credible—avoid fluff.
   
   Expand on the product by mentioning cost efficiency, conversion performance, ease of use, and flexibility.
   
   Shorten long company names and locations (e.g., “Love AMS” instead of “AMS Professional Services,” “San Fran” instead of “San Francisco”).
   
   Focus on non-obvious details from the company summaries—small but meaningful things that imply real research.
   
   Avoid generic praise like “Great website” or “Love your marketing.”
   
   The output should always follow the JSON format provided.

   Execution prompt · Source text。Generate Multiline Icebreaker1 node user message (few-shot example input: Maki Agency summaries)

   Copy prompt

   =Profile: Aina Rakotoarinaly, CEO founder - Maki Agency / Ti'bouffe, Maki agency, outsourcing/offshoring, Antananarivo, Madagascar
   
   Website: 
   
   This webpage presents Maki Agency, a professional digital outsourcing company based in Madagascar that specializes in tailored web development, integration, design, SEO, content creation, community management, and more. The agency offers a range of white-label and dedicated resource solutions, targeting businesses that wish to outsource various digital projects. Maki Agency emphasizes its team's versatile technical expertise across major web technologies, including CSS, HTML, JQuery, WordPress, PHP, WooCommerce, Laravel, and Odoo. The company positions itself as an ideal partner for comprehensive digital support, ensuring that client's digital and branding needs are met through experienced personnel and rigorous project management.\n\nThe website details the specific services provided, such as graphic and web design (logos, banners, retouching), web integration (landing pages, newsletters, site layouts), development (showcase sites, e-commerce, intranets, bespoke applications, maintenance), content writing (SEO-optimized texts, articles, product sheets, social media posts), search engine optimization (audits, optimizations, submissions), and social media management. The agency highlights its strengths in quality of work, experience, and discretion, especially in white-label arrangements. Visitors are encouraged to contact Maki Agency for new or existing projects, and convenient contact options (phone, QR codes, social media, chat) are provided for initiating discussions.
   
   This page presents Maki Agency, a Madagascar-based digital agency specializing in web outsourcing and subcontracting services. The agency emphasizes its experience and dedicated team capable of handling diverse digital tasks such as web development, design, SEO, content writing, integration, community management, and maintenance. Maki Agency offers both white-label and dedicated resource solutions for clients seeking to externalize parts of their workflow to a specialized offshore partner. The descriptions highlight the agency's proficiency in popular web technologies, frameworks, and CMS platforms (such as HTML, CSS, PHP, WordPress, Laravel, WooCommerce, and Odoo), as well as its ability to execute projects ranging from landing pages, e-commerce platforms, and intranets to detailed graphic design and content creation.\n\nThe site underscores Maki Agency's core values and competitive advantages, such as meticulous attention to detail, experienced professionals, creativity, discretion, and a client-focused approach. It provides detailed breakdowns of service offerings, ranging from graphic materials (logos, flyers, banners), technical integration, app and website development, staff outsourcing (developers, designers, writers), SEO strategies, community management, and digital content production. Contact details and multiple avenues for communication (phone, WhatsApp, Skype, QR codes) are prominently featured, along with encouragements for clients to reach out for consultations or ongoing projects requiring outsourcing. The agency also highlights its longevity and adaptability in the digital sector, supporting clients across various industries and digital competencies

   Execution prompt · Source text。Generate Multiline Icebreaker1 node assistant message (few-shot example output)

   Copy prompt

   {"icebreaker":"Hey Aina,\n\nLove what you're doing at Maki. Also doing some outsourcing right now, wanted to run something by you.\n\nSo I hope you'll forgive me, but I creeped you/Maki quite a bit. I know that discretion is important to you guys (or at least I'm assuming this given the part on your website about white-labelling your services) and I put something together a few months ago that I think could help. To make a long story short, it's an outreach system that uses AI to find people hiring website devs. Then pitches them with templates (actually makes them a white-labelled demo website). Costs just a few cents to run, very high converting, and I think it's in line with Maki's emphasis on scalability."}

   Execution prompt · Source text。Generate Multiline Icebreaker1 node user message (runtime dynamic variable)

   Copy prompt

   =Profile: {{ $('Loop Over Items1').item.json.first_name }} {{ $('Loop Over Items1').item.json.last_name }} {{ $('Loop Over Items1').item.json.headline }}
   
   Website: {{ $json.abstract.join("/n") }}
   
   Product Description: {{ $('Details').item.json["About your Product"] }}

7. Append to Google Sheets

   Add Row1 (Google Sheets node, operation=append) appends the final outreach content and lead metadata to the specified spreadsheet. It maps 8 columns: first_name, last_name, designation, email, website_url, location, phone_number, Outreach Content. Create the sheet and authorize credentials beforehand.

You are an n8n workflow setup assistant. The user wants to replicate the "Deep Multiline Icebreaker" template: submit product info via form, automatically scrape prospect websites, use GPT-4.1 to generate personalized cold-email icebreakers, and write results to Google Sheets. First confirm the user has: 1) an n8n instance; 2) OpenAI API key; 3) Google Sheets OAuth write access; 4) Apify API token or an alternative lead source. Then guide them to import workflow ID 13282 from the n8n template library, configure credentials, form fields, Google Sheets document ID and sheet name, and suggest testing with Limit1=1 before scaling.