Clay is expensive. So i'm building a Clay.com alternative in Google Sheets, and I wanted to share that with y'all. Maybe it will give you an idea on how to build it.

One underrated thing, that many seem to overlook is how much time you can gain back from automating sales admin. Especially when you are about to scale your outbound marketing. Ngl a 3 step workflow in N8N just like this saves me a ton of time. Just sharing this as an ideation for you guys, Slack has also been a centralized hub of notifications for me. Pretty neat!

Everyone’s chasing automation. But most aren’t asking the real question... "Why should anyone care about this?" You can scrape leads, write icebreakers, build full flows. But if your offer is dull, none of it matters. It’s not about volume...it’s about weight. Before scaling.. Does your offer feel urgent? Does it speak to a real pain? Can it stop someone mid-scroll? Fix the message first. Then hit send.

Basically this trick helped me go from 283 minutes down to 18 minutes for enriching 1000 leads Now it's the backbone of my client systems and my cold email workflows. I spent some time working through it last week, and it's a very simple tweak tbh : 1. Update your n8n instance — If you’re self-hosted, search for “How to update n8n on Hostinger” or wherever you’re hosting it. You’ll need the latest version to access the new parallelization features. 2. Convert your enrichment process to a Subworkflow — Right-click on the module you want to parallelize and click “Convert to Subworkflow.” 3. Set the Subworkflow to run asynchronously — Inside the Subworkflow config, select “Run Once for Each Item” and deselect “Wait for completion.” This is the key step to run batches in parallel. 4. Use ‘Split in Batches’ or ‘Loop Over Items’ — Feed the input data (e.g., leads from Google Sheets) into a Split module to break it up into batches of 15, 30, etc., depending on your API rate limits. 5. Pass each batch through the Subworkflow — Each batch now gets processed in parallel, giving you up to 10x+ faster lead enrichment — especially useful when dealing with LinkedIn scraping, OpenAI summarization, and icebreaker generation like I do. ⚠️ Heads up: Going too far (e.g. 50+ concurrent runs) may hit API rate limits, so adjust depending on your tools. If anything’s unclear or if you want the exact setup I use, let me know. Hope this helps you 🙏

most ai icebreakers suck. they’re generic, robotic, and get ignored. but if you do it right, ai personalization can 2x your cold email replies —turning 1 booked call/day into 2 and even more… without sending more emails. here’s how to do it 👇 why it works - decision-makers get 8–20 cold emails/day. yours needs to stand out. - personalization is an amplifier: 3% reply rate → 6% reply rate. - but ai should only write your icebreaker, not the whole email. step-by-step 1. scrape lead data from linkedin using apify or EXA AI 2. send that data to ai with a good prompt (rules, examples, clear tone) 3. ai writes 1–2 sentences (the icebreaker) 4. you write the rest of the email yourself 5. send & watch replies go up prompt tips - tell ai who it is (“you’re an sdr writing warm, specific compliments”) (using the system prompt) - feed it rich inputs (job title, niche, achievements, signals) - set rules (no full names, warm tone, under 2 sentences) - use placeholders for specific signals + metrics you want referenced here's the prompt if you wanna copy it : We just scraped a linkedin profile. Your task is to take their summaries and turn them into catchy, personalized openers for a cold email campaign to imply that the rest of the campaign is personalized. You'll return your icebreakers in the following JSON format: { "icebreaker": "Cool move building out/That shift into {thing} stood out/Smart play using {superSpecificThing}, especially the part about {specificSignal}.\n\nNoticed {anotherThing} came up too, so figured I’d reach out with something that might be helpful." } Rules: - Keep the tone warm, simple, and friendly, like you're talking to someone at a coffee shop. Think 3rd or 5th grade reading level. - No full names in the icebreaker. That reads too robotic. - Make sure to use the above format when constructing your icebreakers. We wrote it this way on purpose. - Mix up the first sentence starter using warm, friendly phrases pick what fits best based on what you're referencing.