Architected and deployed a full production B2B SaaS platform for restaurants, bars, and hospitality businesses with active daily operations and paying subscribers.
Key Engineering & Product Highlights:
• Integrated AI Operations Assistant: In-app conversational assistant powered by Google Gemini API, allowing restaurant managers to query sales velocity, stock anomalies, and daily operational metrics in real-time.
• Granular Inventory Engine: Real-time ingredient tracking down to the gram/milliliter linked directly to recipe consumption upon checkout.
• Real-Time Kitchen Sync: Bi-directional WebSocket events keeping order queues synchronized across multiple kitchen stations with zero page reloads.
• Multi-Branch & Multi-Tenant: Robust tenant data isolation, custom role-based permissions (Cashier, Waiter, Kitchen, Admin), and multi-location management.
Summary: A suite of 20+ developer utilities that run entirely in
the browser. No uploads, no server, no data leaving your machine.
What I did: Built the full stack — Next.js frontend, Web Workers
for heavy processing (formatting tens of thousands of lines of JSON,
PDF manipulation, hashing) so the UI never blocks. Every tool works
offline after first load.
The no-upload promise is the strongest part. I'd make the offline state visible in the UI, so someone working with sensitive JSON or PDFs can see that the file stays on their machine before they drop it in.
AI Lead Qualification & Appointment Automation System
AI Lead Conversion Platform — Telegram, CRM & Automated Scheduling
Designed and developed an AI-powered lead conversion system that handles incoming Telegram conversations from first contact to qualification, CRM synchronization, and appointment booking.
The AI works with conversation history, lead profile data, unanswered questions, current funnel stage, available actions, and verified CRM data to determine the next appropriate step and generate structured responses.
The system automatically creates and updates leads in the CRM, manages qualification stages, books meetings, generates Yandex Telemost links, sends reminders, handles rescheduling, and escalates exceptional cases to a human manager.
The architecture includes dialogue state management, message deduplication and batching, PostgreSQL persistence, concurrency protection, validation before actions are executed, and safeguards against sending unverified or prohibited information.
This is not just an AI chatbot — it is an automated sales workflow that connects Telegram, AI, CRM, scheduling, and human escalation into one controlled process.
AI makes decisions within controlled business rules instead of operating as an unrestricted chatbot.
The concurrency safeguards and validation-before-actions detail is a strong distinction here—booking systems usually fail at the edges, not in the happy path. I’d expose a compact lead state to the operator (stage, next action, last unanswered question) so a human can resume...