Mansoor A.

Week 2: Building in Public The CSV situation got worse before it got better. What started as a few files turned into this 1. Live job board scrape coming through n8n 2. Do Not Contact list 3. Contacts assigned to reps 4. Contacts not assigned to reps 5. No relationship companies 6. Past clients/companies Looks like the problem is growing, not shrinking. But this was intentional. The only way to clean the data was to separate it first: Contacts → Companies → Relationship status Not elegant. But necessary. Once that was clear, the next step was obvious Merge everything back into one system. That’s where the real challenge showed up. Not enrichment. Not structure. Deduplication - without losing context. Because this is what the data actually looks like → Multiple contacts per company → Multiple reps per company → New contacts with new companies → New reps getting auto-assigned → And trying to reuse V1 enrichments to save credits Everything overlaps. If you dedupe too aggressively → you lose context If you don’t dedupe enough → you waste credits and create noise I used "single-row lookup" in Clay, with normalised URLs as the anchor. It works. But... I wouldn’t call it “solved.” I can already see the tradeoff → Save credits → Or preserve quality And right now, it feels like you can’t fully have both. I'm going to explore Claude for this on Sameer's recommendation. Do you optimise for cost or for data integrity when deduping messy GTM systems? I've shared screenshots of V1 and V3 Overviews. More soon. --------------------- Mansoor

Week 1: I got handed 4 CSVs and a problem. I gave back a system. Jumped on a call with the client to understand the data structure and the enrichment work that already existed. The challenge wasn’t the enriched data. It was understanding V1 and V2 - both were already built and already feeding data into a sequencer. Understanding V1 is the hardest part. V2 is much more straightforward. Whereas V1 is a rabbit hole. You can see the complexity in Miro board screenshots below. The major enrichments in there were → Scoring and tiering based on titles → Mapping contacts against the representative at the company (client side) Tools used 1. Clay 2. Miro 3. Fathom.ai You might wonder why Miro and Fathom matter here. They’re basic tools. Everyone uses them. But these two alone saved me a lot of effort. Because the data was messy, I had to keep going back and forth through the call recording, while mapping logic and data flow on a Miro board before even thinking about building V3. The most time consuming part of this project wasn’t building. It was understanding how data actually flowed through V1. Data points Contacts → previous relation → no relation → previous relation but new company Companies → previous relation → no relation → new company Live signals → n8n scrape from job boards All of this had to be merged and deduped - without losing any meaningful contact or context. Still early. Still messy. More soon.

The Chemical Deep-Dive Finding specific chemical buyers by teaching AI to read manufacturing recipes. A leading chemical manufacturer in Pakistan recently came up with a challenge. Challenge: They had a stock of "Ethylamine" sitting in an overseas warehouse, but no clear list of who actually needed it. The easy route would have been to scrape a generic list of "Chemical Companies" and call it a day. In my experience, that’s just building on sand. Here was the workflow: -> Look-alikes: I identified known buyers and mapped their characteristics. -> Qualification: I used AI to crawl domains and LinkedIn to verify if they were actual manufacturers or just distributors. 🔍 -> The "Recipe" Filter: This was the breakthrough. I used AI to analyse their specific product lines to see if "Ethylamine" was a necessary ingredient in their manufacturing process, and whether they are a regular buyer. It wasn't about finding more leads; it was about finding the specific ones where the chemistry actually matched. 🧪 The result? I built a sample table, and it created an immediate spark. I’m really enjoying this transition into GTME. How are you using data to find the "needles" in your industry?

Hi folks - I want to download search results (csv) from sales nav. Any one knows good and safe way around doing this without getting flagged. There's clay, Apollo and Instant data scraper that I know of. IDS and clay doesn't allow this. Need help..