ShippedLocal Business AI
// build study

Reply Rail

AI-drafted Google, Yelp, and Facebook review responses for local businesses — one queue, one click.

Client:Multi-location F&B chain (NDA)
Duration6 weeks
ScopeFrontend MVP for a multi-location F&B chain

// Google, Yelp, and Facebook in one inbox — drafted replies for every one

// the numbers

Figures from the engagement, shared under NDA.

We publish them unchanged and can’t break them down any further here. The reference build you can open runs entirely on sample data.

25+Reviews queued
6Locations
01In brief

If you read one part of this page, read these 3 lines.

  • Unified inbox — Google, Yelp, and Facebook reviews in one queue
  • Drafted replies with three tones and platform-aware character limits
  • Themes panel with AI-extracted topics and sentiment-colored bars
02Overview

What it does — and which part of it we built.

Pulls reviews from Google, Yelp, and Facebook into a single queue, drafts a tone-matched reply for every one, and tracks sentiment trends across locations — so a small business owner stays at under-24h response time without writing a word.

03The screens

Every screen here is from the reference build, not the client’s system.

The captions say what you are looking at. Every name and record on them is sample data.

04Outcomes

What the engagement left the client with.

  • Average response time held under 24 hours across 6 locations
  • Owner spends ~10 minutes a day on reviews instead of an hour
  • Sentiment trend visibility per location for the first time
05How it is built

The stack was picked per constraint, not per house habit.

4 technologies across 1 layers — the shape of the stack follows the problem.

Frontend & Mobile
Next.jsTailwindFramer MotionTypeScript
Every feature in the build (5)
  • Unified inbox with AI urgency lanes (Urgent / Reply soon / Auto-thanked / Quiet)
  • Drafted replies with three tone presets and platform character limits
  • Themes panel: AI-extracted topics with sentiment-colored bars
  • 12-week multi-platform rating trend chart
  • Per-location scorecard with top complaint and top compliment
// see for yourself

Don’t take our word for it — it is running in the frame below.

This is the same page the provenance block links to: our reference build for Reply Rail, with its own look, copy and motion. Scroll inside it, or open it full-screen.

// more from the lab

A team that ships across the board.

36products in production
8industries served
68+technologies in play

Closest to Reply Rail

// next

Building something in this space?

A 30-minute call is enough for us to understand your situation and tell you whether we're the right team. Usable version in the first two weeks if we are.