A selection of automations, agents, and apps we built to sharpen the craft. Some were prototyped for sectors we wanted to learn cold. One is a personal project we still use. All of them taught us how to ship faster for the next one.
A personal project. Claude-inspired UI, a vector database of 65 PDFs, four modes of working. The most polished of the set, and the one still in active use.
Built this the month before my own university finals, partly to study and partly to see how far a single person could push a Claude-style app in a weekend. Kept it open for a few friends. It still gets opened every exam season.
Each of these is a working prototype: built end-to-end, not a slide deck. Filter by what you care about.
Captures bookings from WhatsApp, parses out the time, name, and any special requirements, then sends a reminder before the slot and a feedback message after. The same mechanic works for viewings, consults, and coaching sessions.
Logged to: a Google Sheet with name, date, time, requirements, feedback, and status.
Three pipelines running at different cadences. Daily review scrape, weekly theme detection, quarterly sentiment trend. The owner gets a WhatsApp digest, the rest lives in a web dashboard.
The interesting bit: the 12-week pipeline replays metrics it stored weekly, so trends are real data, not snapshots.
Pulls a day's orders, cross-references the product catalogue, and writes a plain-English summary for the owner on WhatsApp or Slack. Built standalone, and just as useful plugged on top of a Shopify or POS export.
Honest take: most storefronts already export raw sales data. The real value is turning those reports into a daily plain-English message someone will actually read.
Notices when a repeat customer has gone quiet, pulls what they bought last, and drafts a warm WhatsApp message with the right details slotted in. Approved templates with AI-written variables underneath.
Where this goes next: a building block in a wider D2C retention and loyalty system, not a standalone product.
A chatbot that knows a coaching center's offerings cold and answers parents and students with the same patience at 11pm as at 11am. WhatsApp-ready, built to plug into the channel the center already uses.
The interesting bit: a two-way training mode lets the owner roleplay with the AI to tune answers before going live.
Scrapes Google for a target type of business, then runs each result through configurable qualifiers before it ever lands in the sheet. The qualifiers are the product: LinkedIn presence, valid website, email visible.
What makes it useful: the qualifiers are configurable per run, so the same pipeline becomes a different list with one toggle.
The next one we build could be yours. Tell us what's eating your week and we'll come back with a plan.
Start a Conversation