Web app · risks against a standard · Word with tracked changes
Contract review
A lawyer spends hours on the same things: 100% prepayment, unlimited penalties, court in the counterparty’s region, “silence means consent” on acceptance. Here the company standard is written as rules: the contract is split into clauses, each is checked against the standard, and every risk found comes with an explanation and ready wording. The lawyer accepts, edits or keeps it — and sends the counterparty the changes in familiar Word.
Scenario: Zerno coffee roastery — fictional: reviews contracts from a green coffee supplier, a service company and a packaging manufacturer. You can upload your own contract too.
Open the demo
The contract is checked right in the browser: the text and files are not sent anywhere.
The app runs in your browser: nothing is sent to a server.
What the demo shows
How to try it
Open the supplier’s draft
A green coffee supply contract — risk 91 out of 100: 100% prepayment, 0.5% daily penalties and a court in Krasnodar are underlined.
Review a risk
Click “100% prepayment” — an explanation, the standard and suggested wording open on the right. Accept the change and the risk scale drops.
Rewrite it your way
In the service contract, open “Silence means consent”, click “Edit” and enter your own wording — it goes into the Word file and the protocol.
Change the standard
In “Company standard”, set the warranty to 3 months or more or choose another court — the findings are recalculated instantly.
Download the documents
“Word with changes” opens in review mode with comments, alongside the disagreement protocol and a clean copy.
No paid neural networks
Risks are found by rules: they know typical wording in supply and service contracts and compare numbers with the standard. In a production project the clauses are read by a language model — it understands any wording and writes the explanation, while the standard, rules and final changes stay with the lawyer.
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
- A language model (GPT, Claude, YandexGPT or GigaChat) reads clauses in any wording, and the standard’s rules verify its conclusions
- Standards for different contract types — supply, services, lease, construction — maintained by the lawyer without a developer
- Review on your own server: contracts don’t go to external services
- Contracts from email, a document management system or 1C, with approval in Telegram: the lawyer gets a ready review
Stack
- All demos by stack:
- React
- TypeScript
- React 19
- TypeScript
- docx
- JSZip
- Zustand
- Vite
- Tailwind CSS
Developer’s comment
Anton Goncharov
AI systems developer · Python
For business
- A standard contract is reviewed in minutes rather than half a day: the lawyer spends time only on disputed clauses.
- Risks are shown in money — how much in penalties will accrue, who pays for downtime — so they’re understood not only by the lawyer.
- The counterparty receives changes in familiar Word plus a disagreement protocol — negotiations go faster.
For developers
- The contract is split into clauses by numbering; every rule has a check, a quote for highlighting and a fix function, all covered by tests on three contracts.
- The Word file is built in the browser with the docx library: real insertions and deletions (w:ins, w:del) and a comment with the reason for each change.
- The clean copy is loaded back via JSZip and passes the check with no findings — that’s a test too.
Tips
Tip 01
First write down the standard: which terms the company accepts without negotiation. Without it, a review is just an opinion.
Tip 02
Give ready wording for every risk — “this clause is bad” without a fix hardly helps a lawyer.
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 · 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 · marketplaces · moderation check · unit economics
Product listings for WB and Ozon
The agent turns a supplier’s text into two listings — for Wildberries and for Ozon: a title within the marketplace limit, a description with search keywords, attributes from the reference lists. Then it checks what listings usually fail moderation on and calculates what’s left from each sale.
- 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