The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Processed 2,956 parking lots using Clay. Scraped satellite screenshots, ran AI analysis on each one to detect lighting fixtures, and categorized results automatically. Client needed to know which lots had proper lighting for a property upgrade assessment. Built the entire pipeline in Clay with automated screenshot capture + AI vision analysis. 2,956 rows, 14 columns, zero manual work. This is what Clay can do when you build the right workflow.
Vision calls across ~3,000 rows can drift on edge cases like glare, shadows, or tree cover. Did you spot-check a sample against ground truth, or add a confidence column to flag uncertain lots for review?
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
A wall I walked past turned into my latest experiment with photogrammetry.
I took a quick, rough video scan while out on a walk, mostly to see what I could get out of it. What impressed me was how little time it took to get something usable (some cleanup would be necessary for a production shot).
Still experimenting, but there’s something exciting about turning an everyday surface into a 3D asset without making a whole project out of it.
Pretty cool result for a quick walk scan. Which app did you use to capture it?
Would you send an AI icon set straight to a client? 👀
I tested Ideogram Vector on a pixel icon set for Yue Fang, an interior decorator with Chinese inspirations. The icon set was for her services.
After a few tries & prompt refining, Ideogram nailed the vibe!
BUT, some things needed to be reworked:
➡️ the white parts were shapes stacked on top of a solid black shape, not real cutouts (surprise when you open the SVG 💀)
➡️ some pixels weren’t actually square
➡️ some pixels were bigger than others
➡️ icon sizes were all different
Pixel art is supposed to be the ONE style where everything sits on a grid lol
So, which set would you hand to the client?
11 voted
34%
21 voted
66%
32 votes
Closed
Stacked shapes instead of real cutouts is exactly the kind of flaw that only shows up when you open the file. AI gets the vibe fast, but the file-level check before handoff is still on us.
You need a strong starting point for a sales-tech brand without trying too hard.
A generic SaaS template won’t work in this case.
What you need are:
• Sales-focused product UI
• Personalized outreach with follow-up and reply intelligence
• Pricing, testimonials, FAQs, and integrations
• CMS for blog posts, feature pages, and case studies
• Clear paths to demos and trials
That’s how we designed Avina, our new Framer template.
Built for AI sales products, outbound automation tools, and sales-focused SaaS products.
Avina is designed around a real outbound sales journey.
So visitors understand quickly.
Check the link in the comment.
What I like here is the focus on the actual sales journey, not just the visual design. For AI sales tools, showing how outreach, follow-ups, and reply handling connect to real outcomes can make a big difference. Curious how you approached that in Avina?