Working bots and web apps built around fictional businesses: the same approach as in client projects, just without paid neural networks.
I build demos the same way as client projects: tests, CI, deployment only after a green build. What you see here is the same level of work you’ll get.
Where to start: one or two live demos from each section.
Telegram and Max · knowledge base search
A first-line bot answers customers from the company knowledge base, shows the source of each answer, honestly says “I don’t know” and hands the conversation to an operator.
▶ Open live demo
Telegram Mini App · payment · statuses
A catalog as an app inside Telegram, a cart, test payment and order status notifications — from “packing” to “delivered”.
▶ Open live demo
Web app · question → SQL → chart · PostgreSQL in the browser
A manager asks in plain words — “revenue by channel for Q3”, “which customers stopped ordering” — and gets SQL, a chart, a table and a conclusion. The sales database is real PostgreSQL running right in the browser.
▶ Open live demo
Web app · risks against a standard · Word with tracked changes
A counterparty sent their own contract — the review compares it with the company’s standard, highlights risky clauses, explains why they’re dangerous and suggests wording. The output is a Word file with tracked changes and a disagreement protocol.
▶ Open live demo
Web app · RAG · neural network in the browser
How a support bot finds an answer in a knowledge base: documents are cut into fragments, search runs by keywords, by meaning or as a hybrid, and every fragment found shows why it ranks above the others.
▶ Open live demo
Next.js corporate logistics website · calculator, tracking, AI request
A transport company’s corporate website: a calculator that compares groupage and a dedicated truck at once, shipment tracking with the truck on a map, AI parsing of a request from an email or waybill with missing fields highlighted, a map of warehouses and terminals with a storage calculation, a carrier application with an eligibility check, and company details with checksum validation.
▶ Open live demo
Web app · speech recognition · neural network in the browser
A customer dictates a request by voice, and the manager gets a ready card: name, company, phone, budget, timeline, task and a score — hot lead or not. Speech is recognized by Whisper right in the browser.
▶ Open live demo
Python backend · webhooks → amoCRM and Bitrix24
Leads from the website, ads, calls, email and bots arrive at webhooks, are normalized, checked for duplicates, routed to managers and delivered to amoCRM and Bitrix24 — with retries when the CRM is unavailable.
▶ Open live demo
WordPress and WooCommerce · runs in the browser
A live WooCommerce store: 15 products and 70 variations, a selection quiz, instant search, favorites and quick view, reviews and promo codes, CDEK and Russian Post delivery by postcode, YooKassa-style payment, company purchases with tax ID validation and one-click orders. WordPress runs right in the browser — you can place an order and go into the admin panel.
▶ Open live demo
Anton Goncharov
AI systems developer · Python
Tip 01
Build demos the same way as production: tests, CI, automatic deployment. Otherwise the demo will drift from what you can actually do.
Tip 02
Show where the system says “I don’t know”. It builds more trust than perfect answers.
