Hello guys, This is my first project using Clay, nothing crazy. But working as a BDR i know how hard and time consuming was to look for contact for brick and mortars business that live outside of LinkedIn. This is why i created this table using the Google Maps function and then used AI to enrich it with the legal company name, administrator's name,email and phone number but also with Internal Champions's ( ICs) Name, position email adress and phone number, but every person that ever did hunting knows that just the name of the right person is enough. I would love to share it with somebody and get feedback about how I could improve and optimize it for scale, as i belive that +300 credits for 25 rows might not be the best use case. Thanks!
Hey Rares A. This is actually a really solid use case for Clay. A lot of people focus only on SaaS/LinkedIn workflows, but local brick-and-mortar prospecting is where Clay can create huge leverage because the data is usually fragmented and painful to gather manually. The Internal Champions layer is the most interesting part to me - even just identifying likely decision-makers for restaurants/hospitality businesses saves hours of research for BDRs. For optimization, 300+ credits for 25 rows does feel high, so Iβd probably:
add conditional runs (βonly enrich if field is emptyβ)
separate high-confidence vs low-confidence enrichment waterfalls
avoid running AI on every row upfront
use cheaper providers first before triggering Claygent/AI steps
But overall this looks like a strong real-world workflow, especially for agencies targeting SMB/local businesses.π
