Case study
Feedlify: an AI feedback platform, built solo
A feedback platform that gathers customer requests from wherever they come in, uses AI to merge the duplicates, and tells people when what they asked for ships.
- Role
- Design and build, solo
- Status
- Launching 2026
- Built with
- React, Supabase, Clerk, OpenAI, Jira, Resend, Stripe, Sentry
The problem
Customer feedback comes in from lots of places. The same request shows up several times in different words, and the person who asked for it rarely hears back when it finally ships.
What it does
Feedlify collects the feedback, sorts it with AI, turns what's worth building into a Jira ticket, and tells the customer when it's done.
- Collects feedback from wherever it comes in
- Uses AI to find requests that mean the same thing and merges them
- Creates Jira tickets for what's worth building
- When a ticket's status changes, notifies the customers who asked. The product manager sees the rendered email before anything is sent.
What I built
All of it, on my own: the interface, the database with row-level security, sign-in, the Jira integration, background jobs, AI clustering, the notification engine, payments, and error tracking.
What it means for client work
The same problems come up in small-business projects. The AI has to get things right before anyone trusts it, it has to work with the tools a team already uses, and each customer's data has to stay separate. Feedlify is where I worked those out.
Services
Let's see if I can help.
Tell me what you need, or what's wrong with the site you have now. I'll reply by email, and if it makes sense we can set up a free 30-minute call. You're not signing up for anything.