The situation
Building one site per advisor by hand does not scale, and static sites go stale the day a property sells. The network needed hundreds of sites that never fall out of date.
Automation · Websites
Each advisor in the network needed a personal site that stays in sync with their listings. We built a factory: the advisor's record is written once, and a page is rendered for them on every visit from shared templates.
The situation
Building one site per advisor by hand does not scale, and static sites go stale the day a property sells. The network needed hundreds of sites that never fall out of date.
What changed
A generator writes each advisor's record; an edge worker renders the page on request from four templates with a closed set of placeholders. A template change reaches every site at once, and a sold listing disappears without anyone redeploying anything.
How it works
The platform sends the advisor's profile and listings.
A language model writes the advisor's page text from the record.
The record is saved in a global key-value store.
A worker fills one of four templates through a closed placeholder contract.
Template changes and sold listings take effect on the next visit.
Where the AI stops
The model
The code
By the numbers
Built with
Built for
Real estateSaafkaA network of real-estate advisors: buy, sell, rent and appraise anywhere in Morocco.Read the client storyMore use cases
Contact
Write to usWe answer the same working day.