Every project below started with an audit, ships with monitoring, and stays with its owner. New cases are added as they go into production — not before.
#01
sabertabatabaei.com
My own brand · Vancouver, Canada
In development
Problem
I needed a working demonstration of the way I claim to build — bilingual, honest about method vs. history, and with an AI diagnostic tool that produces something specific enough to defend.
Solution
A Next.js site with an AI Readiness Audit powered by Claude, a document-grounded assistant (Nova) using Voyage embeddings, dual payment gateways, and a full admin panel — deployed on Vercel and Supabase.
Outcome so far
The audit engine generates personalized reports in ~30 seconds with a schema-validated fallback path if the model is unreachable. Monitoring, cost limits, and error handling are baked in from day one — because the site itself is my day-300 test.
Running since
July 2026
Stack
Next.js 14TypeScriptSupabase Postgres + AuthAnthropic ClaudeVoyage AI (RAG)VercelStripe + ZarinpalResend
#02
ReplyPilot
Concept build · no client yet
In development
Problem
Local businesses juggle reviews and DMs across Google, Instagram, WhatsApp, and Telegram with no single place to keep replies on-brand and timely — and most AI reply tools either sound generic or send something risky with no human checking first.
Solution
A unified inbox behind one channel-adapter interface, so live integrations and still-pending ones (Google/Meta approvals take weeks — Telegram needs none) share the same code path. Claude drafts replies in the business's own voice with structured-output validation, a do_not_say filter, and a prompt-injection wall around customer content — nothing sends without approval.
Outcome so far
Same discipline as the audit engine above: row-level security from the first migration, a central logger with auto-redaction, and the public interactive demo below, protected by three layers of rate limiting so the cost stays predictable before there's a paying customer.