Project · 2025
Meta Ad as Signal to AI-Powered Outbound
A system that finds real estate companies the moment they start running Meta lead-gen ads, and reaches the right person there with a message written for them specifically, not a template.
The signal
The CRM is built for real estate companies running lead-gen ads on Meta. So one of the strongest buying signals is simple: a company that just started running those ads. The moment that happens, we want to be the first ones in their inbox, not the fifth.
n8n, Apify, Clay
Instantly
Finding every new advertiser
Fetch on a schedule
An n8n workflow runs periodically and pulls every company currently running ads through Apify's Facebook Ads Library Scraper.
Track everything we've seen
Apify has no way to filter to just "new" ads, so a BigQuery database keeps a running record of every page and ad seen. New activity gets found by diffing against it.
Filter and enrich the new ones
Each row is checked: is the page category real estate? Is the ad already in our database? If it's genuinely new, a second Apify actor pulls the full page profile, and an HTTP request pushes it into Clay for the next stage.
Alert the team
The same workflow fires a Slack notification, so new companies showing up in the pipeline are visible in real time, not just in a dashboard someone has to check.
Qualifying the list, with AI doing the filtering
Confirm they're in the UAE
Checked first by phone number or address, using a free formula, so no AI credits are spent unless needed.
If that's inconclusive, a cheaper GPT model tier (about 6x less expensive, since overkill isn't needed for a task this simple) resolves location from the company's website or Google profile instead.
Confirm they have a valid website
Same pattern: a free formula check runs first. Only rows still empty after that get an AI web crawl to find one, which keeps credit spend down by not running AI on rows that don't need it.
Find the right people
From the filtered list of UAE-based companies with valid websites, Clay identifies the Sales Managers, Marketing Managers, and Owners at each firm.
Enrich emails with a waterfall
Email addresses are found through waterfall enrichment across Lead Magic, Apollo, and Prospeo, trying each provider in turn to maximize the hit rate.
Writing to each person differently
A CEO, a Sales Manager, and a Marketing Manager care about different things, so the emails aren't the same. Every email is generated through multi-step AI prompts, using the actual ad the company is running as the personalization hook.
CEO
the AED 200K gap angle in your Meta ad
Hi Paul, Your ad is pretty blunt about it. Pick the wrong unit and investors lose AED 200K+. Switching someone from a trendy apartment to a high performing villa is exactly the kind of advice that closes deals, if the follow up call happens before they cool off. Does your team's CRM actually get used, or does it sit there while those "buy based on math" leads go stale? The CRM is built so agents actually use it. Fast follow up, nothing slips through. Want a quick look at how many leads from this ad have already gone cold? Saqib
Sales Manager
your villa vs apartment leads not converting due to speed
Hey James, Your ad promises real ROI numbers and profit projections. That's the kind of detail that pulls in investors who are ready to move, not just browsing. Are your reps logging follow ups fast enough to catch them while they're still comparing villa vs apartment numbers? Or does stuff slip because updating the CRM is a hassle? The CRM auto assigns leads and nudges reps to follow up. No manual entry, just faster response. Want to see how fast your reps are actually following up right now? Saqib
Marketing Manager
visibility into your financial guide meta leads
Hi Ali, The financial guide angle is smart. Real ROI numbers, profit projections, top performing launches. That pulls in buyers who actually want data, not just brochures. Here's the gap though. Once someone downloads it and gets handed to sales, do you ever find out if they bought it? Or does the trail just stop at "lead submitted"? The CRM follows every lead from that form all the way to close, so you can see which angle, which goal (ROI vs rental yield vs lifestyle), and which launch actually turns into revenue. Not just cost per lead. Want a quick look at what that'd show for your last few campaigns? Saqib
Emails are generated on Clay using the ad context, then pushed to Instantly for the send sequence.
Results
Lead funnel for the Sales Managers campaign, six weeks in:
"Interested" sits at 0% because that status isn't actively tagged in this tool. The 308 replies (6.0%) are the real signal, and are triaged manually from there.
Why it works
- Strong signal of someone already spending on Meta
- Highly personalized emails, not templates
- Different messaging for different roles at the same company
- First in the inbox, right after they start running ads, before anyone else reaches out
What happens after a reply
Replies are handled and handed to the sales team for calling. From there: calls → demo booked → demo given → follow-up calls → payment and contract.
Slack
OpenAI
Apollo
ZeroBounce