Telegram and Max · leads and CRM
Lead qualification
Customers write however they like — even everything in one message. The bot extracts card fields from the replies, asks only about what’s missing, scores the lead from 0 to 100 and sends the manager a ready card instead of a chat thread.
Scenario: A development studio receiving requests for bots, websites and automation.
Open the demo
The bot replies in Russian: it was built for Russian-speaking customers. Example phrases come with translations.
Don’t enter real personal data: this is a demo, and everything is deleted after 24 hours.
What the demo shows
How to try it
Open the bot
The “Open in Telegram” button or the QR code. Press “Start”.
Describe the task
As you would to a contractor. You can include the budget, timeline and contact right away — the bot will sort it out.
Answer follow-up questions
The bot asks only for what’s missing. Budget and timeline have quick-reply buttons.
See the result
A deal card with a score arrives in the chat. The /board command shows all leads — names are hidden there.
What to write
- Нужен Telegram-бот для записи клиентов в салон, с напоминаниями и оплатойI need a Telegram bot for salon bookings, with reminders and payment
- Сайт для кофейни, бюджет 60 тыс, срок месяц, пишите @usernameA website for a coffee shop, budget 60k, one month, message @username
- От 150 до 500 тысFrom 150 to 500k
- Не горит, можно за пару месяцевNo rush, a couple of months is fine
- Анна, ООО РомашкаAnna, Romashka LLC
Commands
- /start
- new request
- /card
- my card
- /board
- deal board
- /about
- how the demo works
No paid neural networks
In a production project, card fields are extracted by a language model with a strict JSON-schema response. In the demo, rules do the job instead: regular expressions for amounts, timelines and contacts. The dialogue, follow-ups, scoring and board work just as in production.
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
- Field extraction by a model with a JSON schema — understands any wording
- The deal goes straight to amoCRM or Bitrix24 with an owner and a task
- Scoring rules for your funnel: average deal size, region, source
- Requests from the website, Telegram, Max and email in a single queue
Stack
- All demos by stack:
- Python
- Telegram and Max
- Python 3.14
- aiogram
- Max Bot API
- SQLAlchemy
- SQLite
Developer’s comment
Anton Goncharov
AI systems developer · Python
For business
- The manager gets a card instead of a chat thread: task, budget, timeline, contact and score. Hot leads are visible at once, and cold ones don’t eat up the morning.
- Customers don’t have to fill in a ten-field form: they write however they like, and the bot asks only for what’s missing.
- The scoring rules are yours: average deal size, urgency, region. They can be changed without rebuilding the bot.
For developers
- Each message is parsed in full first, and only then does the bot decide what to ask — so answers out of order don’t confuse it.
- In the demo, fields are extracted by regular expressions — budget ranges, “60k”, timelines, phones, @username. In production a model extracts them with a JSON schema, while validation and scoring stay in code.
- The 0–100 score is a transparent sum of points with an explanation, tested like any ordinary function.
Tips
Tip 01
Even with a model, validate the result with a schema, and the phone and amount with code: models make confident mistakes with numbers.
Tip 02
Keep the original messages next to the card: in a dispute about the budget, the manager can see what the customer actually wrote.
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
Telegram and Max · knowledge base search
AI support from a knowledge base
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.
- Python
- Telegram and Max
- live
Telegram Mini App · payment · statuses
A store in Telegram
A catalog as an app inside Telegram, a cart, test payment and order status notifications — from “packing” to “delivered”.
- Python
- Telegram and Max
- React
- live
Telegram and Max · booking, prepayment, reminders
Service booking in Telegram and Max
The bot books barbershop appointments: service, barber and free time via buttons or in a single phrase, prepayment, a reminder with “I’ll come” and “Reschedule” buttons, rescheduling, cancellation and the schedule as the administrator sees it.
- Python
- Telegram and Max
- live
Telegram and Max · points, QR at the till, broadcasts
Loyalty program in Telegram and Max
A bakery guest card right in the messenger: a QR code for the till that changes every minute, points and tiers, every sixth coffee free, points exchanged for coupons, bonuses for friends and segmented broadcasts with marketing consent.
- Python
- Telegram and Max
- live
Web app · scenario · aiogram 3 code
Bot scenario builder
A booking or lead-collection bot is assembled from steps: messages, buttons, questions with phone or date validation, conditions. The scenario can be walked through right away in a Telegram-style preview, and the output is ready-to-run Python bot code.
- React
- TypeScript
- Python