Web app · tasks from chat · kanban · evening digest
AI agent in a team chat
A manager can’t keep up with collecting tasks from the chat: things get lost, deadlines slip, and by evening it’s unclear who closed what. Here the agent reads a sample team chat, recognizes assignments with a name and a deadline, keeps the kanban board and gives an evening digest on a button press or when asked in the chat.
Scenario: Zerno coffee roastery — fictional: the operations chat of Anna, Pyotr, Maria and Igor. Replay a ready-made day or write your own message.
Open the demo
The chat and kanban run in the browser: messages are not sent anywhere.
The app runs in your browser: nothing is sent to a server.
What the demo shows
How to try it
Look at a ready-made day
After loading, a scenario is already processed: four tasks, some closed, the creatives still in progress.
Replay the day
“Replay the day” — messages appear one by one, and the agent replies and moves cards.
Write your own assignment
As Anna: “Masha, check the delivery notes by tomorrow” — a card appears on the kanban board.
Close a task from the chat
Switch to Maria and write “Delivery notes are ready” or “Done” — the card moves to “Done”.
Reschedule or reassign a task
“Move the creatives to Monday” or “Hand the creatives to Masha” — the agent updates the card and replies in the chat. You can do the same in the card on the board.
Fast-forward to morning
Press “Next morning” a couple of times: the agent sends a morning digest and reminds Pyotr about the overdue creatives.
Ask for a digest
The “Evening digest” button or “@zernobot digest” in the chat — a list of what’s done and what’s overdue.
No paid neural networks
Messages are parsed by rules: they recognize an assignment with a name and deadline, “on it” / “done” replies, rescheduling, reassigning and cancelling a task, questions about tasks and a request for a digest. In a production project this step is done by a language model — it understands any wording and still writes cards to the kanban via API.
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 bot in Telegram, Max or Slack reads the team chat (with explicit consent)
- A language model (GPT, Claude, YandexGPT or GigaChat) parses messages and calls kanban tools
- Cards in Yougile, Notion, Jira or Bitrix24; an evening digest to the manager in a private message
- Escalation rules: overdue by more than N days — a separate message
Stack
- All demos by stack:
- React
- TypeScript
- React 19
- TypeScript
- dnd-kit
- Zustand
- Vite
- Tailwind CSS
Based on
Books and university courses whose ideas are at work in this demo.
Book · Gleb Arkhangelsky, Olga Strelkova
Remote Work: A Crash Course in Working from Home
The agent turns assignments from the work chat into cards with an assignee and a deadline and sends a summary in the evening: agreements are written down and the status is visible without calls.
Developer’s comment
Anton Goncharov
AI systems developer · Python
For business
- Tasks from the chat no longer get lost: an assignment immediately becomes a card with a deadline and an owner.
- The evening digest shows in a minute what’s closed and what’s overdue — without collecting statuses by hand.
- The team writes as it always has; the kanban updates itself, and in the morning the agent reminds those with overdue tasks.
For developers
- Message parsing is pure functions with tests: assignment, status, rescheduling, reassignment, cancellation, digest; names in any grammatical case, Cyrillic without the ASCII \b.
- Chat and board are a single source of truth: edits on the kanban (@dnd-kit) go through the same actions as commands, and the agent reports them back to the chat.
- “Replay the day” is the same replay as in the tests, just with pauses for the demonstration.
Tips
Tip 01
Start with assignment templates (“Name, verb by deadline…”) — the agent makes fewer mistakes even without a model.
Tip 02
Send the digest to the manager privately rather than to the shared chat — otherwise the whole team gets pinged in the evening.
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 · 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