Home › Case studies
// cases
Case studies
Every card below is a real build. CLIENT PROJECT means built and handed over to a client; DEMO is something I built to show a pattern; OWN TOOL runs in my own work. Screenshots of Make.com scenarios are captures from the editor.
Make.com automations
Lead Qualification Router
Qualification form → phone-match router → Pipedrive deal → Google Sheets log → "Qualified" / "Not Qualified" tag in ActiveCampaign, before a rep opens the inbox.
Read the case →
Ebook Opt-in Funnel
ClickFunnels opt-in → Pipedrive lookup by email (phone fallback) → new vs. returning routing → person + deal → Sheets → ActiveCampaign tag.
Read the case →
Booking Cancellation Recovery
Cancelled Cal.com call → Pipedrive lookup → cancellation logged → "Call Discovery Cancel" tag → deal moved back a stage so the lead gets a real follow-up.
Read the case →
AI Content Machine
Telegram message (photo, text or voice) → Whisper transcript → GPT-4o post copy → DALL·E image → Google Drive + Sheets → finished post back in Telegram.
Read the case →Lead Processing Pipeline
Website form → HubSpot CRM → Telegram alert to sales → personalised email auto-reply. Zero manual steps.
Read the case →AI Report Generator
Google Sheets data → Claude API summary → formatted report in the owner's inbox every Monday at 9:00.
Read the case →Telegram bots
Telegram Fitness Bot
Bilingual RU/EN bot for a personal trainer: catches Instagram-ad leads, qualifies with branching questions, notifies the trainer, takes payment, delivers guides.
Read the case →
World Cup 26 Toto Bot
Telegram prediction pool: match → winner → exact score wizard, auto-scoring, live leaderboard in the group chat. 11 players, 64 matches, 200+ bets.
Open demo →
MakeFlows Bot
The studio's own Telegram bot: services, pricing, cases and instant lead capture — a living example of what a business bot looks like.
Open in Telegram →AI apps and PWA
PropDesk — AI Staff Assistant
Staff at a property management company describe a tenant issue in plain words and get vendor + tenant drafts with data gaps flagged. Human reviews, nothing auto-sends.
Read the case →
Real-Time Interview Copilot
Windows desktop app: faster-whisper transcription → DeepL translation → Claude agent with a RAG knowledge base deciding when to answer, ask or stay silent.
Open demo →
ArtSmile — Dental Clinic App
Progressive Web App for a dental clinic: TR/RU/EN, online booking with doctor selection, patient dashboard, appointment history, card payment.
Open demo →Describe your process
Which tools are involved, what is done by hand today, how often. I reply within 24 hours with a fit/no-fit answer and, if it fits, a fixed quote.