Web app · marketplaces · moderation check · unit economics
Product listings for WB and Ozon
Suppliers send descriptions any old way: “1000 gr”, “BESTSELLER!!!”, a barcode with a typo, square photos saying “SALE”. A content manager rewrites every listing twice — Wildberries and Ozon have different limits, reference lists and photo requirements — and errors only surface after moderation rejects them. Here the agent builds both listings at once and shows everything that won’t pass before upload.
Scenario: Zerno coffee roastery — fictional: six products from whole-bean coffee to a mug, four of them with problems. You can add your own product.
Open the demo
Best on a computer: the editor, checks and preview are side by side. On a phone you see the product list and the listing one after another.
The app runs in your browser: nothing is sent to a server.
What the demo shows
How to try it
Open the “Ethiopia” coffee
Both listings are ready to upload: the agent read “1000 gr” as 1 kg, split the taste into attributes and wrote a description with keywords.
Look at the mug
Square 800×800 photos and “30% OFF” on the main one — WB won’t accept it. Press “Prepare photos”, then “Set price” — the margin reaches 25%.
Fix the dripper
The agent removed “BESTSELLER!!!” itself and turned off the “hario v60” keyword because it’s someone else’s trademark. A barcode typo remains: change the last digit to 1 — WB will accept the listing, and Ozon will ask for a white background on the main photo.
Fill in the grinder
WB is missing the required “Package contents”, while Ozon doesn’t require it — switch tabs and compare.
Edit the text
Change the title or description by hand — the checks are recalculated, and a button restores the agent’s version.
Add your own product
“Add product” — ready examples or your own text. For a product without a category, the agent asks you to pick one manually.
Export
At the bottom of the listing there’s JSON in the marketplace API format; in the header, a summary of all products in Excel.
No paid neural networks
Listings are built by rules: parsing the supplier’s text, title and description templates for each marketplace, value reference lists and moderation checks. In a production project the text is written by a language model, while limits, reference lists, barcodes and economics stay in code — the model doesn’t decide whether a listing passes.
The demo runs without OpenAI, YandexGPT or GigaChat API keys. Wherever a production system calls a model, there’s a local stub with the same interface — so the demo is free, always available and never makes things up.
What a production project adds
- Texts are written by a language model (GPT, Claude, YandexGPT or GigaChat) from the parsed facts and marketplace rules
- Category and attribute reference lists from the Wildberries Content API and Ozon Seller API, updated on a schedule
- Search keywords and frequencies from marketplace analytics or services like MPStats
- Listings and prices uploaded via API, with moderation statuses returned to the content manager’s spreadsheet
- Products from 1C, MoySklad or supplier price lists; photos processed on the server
Stack
- All demos by stack:
- React
- TypeScript
- React 19
- TypeScript
- Zustand
- Vite
- Tailwind CSS
Developer’s comment
Anton Goncharov
AI systems developer · Python
For business
- One supplier export becomes listings for both marketplaces in minutes rather than a content manager’s day of work.
- Moderation rejections are caught before upload: the barcode, photos, required fields and forbidden words are checked immediately.
- The price isn’t set by eye: you see how much commission and logistics will eat and how much is left from each sale.
For developers
- A listing is a pure function of the product, the marketplace and manual edits: editing a field recalculates checks, economics and JSON without side effects.
- Marketplace rules are data, not code: limits, reference lists, color synonyms and tariffs live in one schema and are covered by tests.
- Only the text is entrusted to the model: the barcode is checked by its check digit, values against the reference list, length against the marketplace limit.
Tips
Tip 01
Pull attribute reference lists from the marketplace API rather than typing them by hand: they change, and a listing silently gets rejected.
Tip 02
Store product facts separately from texts: then a listing for a new marketplace can be rebuilt without rewriting the description.
Want the same for your business?
Tell me about your task — I’ll tell you what from the demo fits, how long it will take and what I’ll need from you.
Other demos in this section
All demos- live
Web app · agent diagram
AI agent builder
A support agent is assembled from blocks: intents, a knowledge base, API calls, checks and operator handover. Send a customer message and watch its path light up on the diagram step by step.
- React
- TypeScript
- live
Web app · question → SQL → chart · PostgreSQL in the browser
AI data analyst
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.
- React
- TypeScript
- live
Web app · risks against a standard · Word with tracked changes
Contract review
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.
- React
- TypeScript
- live
Web app · tasks from chat · kanban · evening digest
AI agent in a team chat
People write in the team chat as usual — “Pete, fix the price list by Friday”. The agent creates a task on the kanban board, moves it through “On it” and “Done”, reschedules and reassigns tasks, reminds about overdue work in the morning and sends a digest in the evening.
- React
- TypeScript
- live
Web app · shared inbox · CRM · protection against bank detail fraud
AI inbox triage
The agent reads the sales team’s shared inbox: it understands what each email is, extracts fields, creates a deal, a ticket or a task in the CRM and drafts a reply. An invoice with new bank details or a phishing email is caught before anyone pays or clicks a link.
- React
- TypeScript
- live
Web app · meeting transcript · minutes · kanban
Meeting minutes → kanban tasks
The agent reads a stand-up transcript and builds the minutes: decisions, tasks with an assignee and deadline taken from live speech, risks and open questions. Tasks go to the kanban board, and at the next meeting the agent moves them through statuses itself.
- React
- TypeScript
- live
Web app · personal data · healthcare · analytics
Anonymizing data before it reaches a neural network
The agent finds full names in any grammatical case, phones, passports, SNILS numbers, cards, addresses and diagnoses in emails and transcripts, replaces them before sending to an external neural network, and restores its answer to the real data on your side. It anonymizes a patient table for analytics so that nobody can be identified.
- React
- TypeScript
- live
Web app · automation · amoCRM, 1C, Telegram
An n8n-style automation pipeline
Three working scenarios of a furniture factory on a canvas, as in n8n: website leads go to amoCRM and to managers by lead temperature, YooKassa payments go to 1C with retries and an error branch, and every morning there’s a digest for the director. Trigger an event and watch records flow from node to node; the workflow can be edited and exported to real n8n.
- React
- TypeScript
- live
Web app · multi-agent system · content
A team of AI agents for content
Six agents prepare a publication from a brief: the editor-in-chief plans, the researcher finds facts in the knowledge base, the writer writes, the fact-checker and editor send the draft back for revision, and the SMM agent adapts the text for Telegram, VK, a newsletter, a blog and a carousel. You see the agents’ entire conversation, every edit and what would have been published without checks.
- React
- TypeScript
- live
Web app · HR · scoring and chatbot
CV screening and an interviewer bot
Twenty CVs for three vacancies are analyzed in seconds: employment periods, experience, salary and city, match with the requirements and a quote from the CV for every “yes” or “no”. What’s missing from the CV is clarified by a bot: it asks only the missing questions, follows up on vague answers and books an interview. Gender, age and family are left out of the assessment.
- React
- TypeScript
- live
Web app · RAG · neural network in the browser
Search sandbox
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.
- React
- TypeScript
- In-browser neural network
- live
Web app · metrics · CI thresholds
Bot quality evaluation
Before a new bot configuration is rolled out, it’s run against control questions. Here you can see how that works: hit@1, hit@3, the share of correct refusals, a comparison with production and a red banner if CI would block the release.
- React
- TypeScript
- In-browser neural network
- live
Web app · AI security · vanilla JS
Prompt injection defense trainer
Try to trick a support bot: coax out a secret promo code, extract the system prompt or get a refund without grounds. Six defense levels, direct attacks and attacks via emails, reviews and the knowledge base, and a check log based on the OWASP Top 10 for LLMs.
- Vanilla JS
- live
Web app · AI economics · vanilla JS
AI bot cost calculator
How much a bot will cost per month on GPT, Claude, YandexGPT, GigaChat or your own model on a rented GPU. Token-based calculation, all models compared on a chart, tips on paying less, and a real o200k tokenizer right in the browser.
- Vanilla JS