How we built it
Write-ups of the products we built and still run. The problem each one solves, the decisions that mattered, and what it does today.
Building AI agents: the hard part is not the model
AI agents are easy to demo and hard to put in front of customers. What we are building, and the four things that decide whether an agent survives real work.
4 min read AI
Site Boost Engine: a growth service we ran on ourselves first
A proprietary growth engine, proven on our own products before we offered it to anyone. Results-driven, with reporting that shows the impact on your metrics.
3 min read Service
Building GetFade: a booking platform barbers actually use
Generic booking tools break in the same three places for barbershops. How we built GetFade around the chair, the walk-in and the regular instead.
4 min read Product
Building LawManager: putting AI inside legal work, not beside it
Document review is where a legal practice loses hours. How we built AI into the workflow of LawManager instead of bolting on a chatbot nobody opens.
3 min read Product
Building RankMetrics: daily rank tracking across 50k+ keywords
Rank tracking is easy for ten keywords and a different problem at fifty thousand. What we built so RankMetrics lands every night without falling behind.
3 min read Product
Building Nilo Learn: designing for children who cannot read yet
Every convention in software assumes a user who can read. Building a learning platform for three to six year olds means giving most of them up.
3 min read Product
Building House Real Estate: search that matches how people actually look for a home
A property marketplace lives or dies on search. What we built for House Real Estate to handle 1,472+ listings and the way people really narrow them down.
3 min read Product
Building AN2Tech Stock: the internal tool we got tired of not having
We built our own inventory system because the spreadsheet had quietly become load-bearing. What an internal tool must get right that a product does not.
3 min read Product