No new app to get adopted
The bot lives in Telegram or WhatsApp, which your team and your customers already use. No training, no app to install: you write, it is recorded.
AI agents
A business bot on Telegram or WhatsApp, in service within a week
Your team enters data, makes requests and receives its alerts from the messaging app it already opens all day long, and your customers get an answer on WhatsApp. Every exchange goes straight into your CRM or your database, with no re-keying.
The market in figures
What public statistics, research and industry studies measure. Each figure links to its source, and when the author sells consulting or AI, we say so.
5.7%
of French companies with 10 to 49 people offer a support chat on their website, with a person or a chatbot, against 8.3% across the EU.
Source: Eurostat, 2025 survey on ICT usage in enterprises, data extracted 14 October 2026
Companies with 10 or more people, excluding agriculture, mining and finance (isoc_ciweb database).
24%
of French small and medium-sized businesses use AI for chatbots, assistants or information search, 10 points more in a year.
Source: France Num, 2026 barometer, 28 September 2026
Public programme of the French Directorate General for Enterprise; 9,655 companies with fewer than 250 employees, surveyed from 23 March to 18 April 2026.
+15%
more issues resolved per hour, on average, for customer support agents equipped with an AI assistant; the least experienced gain the most.
Real data from 5,172 agents at one company, with the assistant rolled out in stages; academic study.
What you gain
No more evening re-keying
An expense, a reading or a request is entered in the field, as it happens, and lands in the right tool. No more notes to copy out or receipts lost in a pocket.
Answers at any hour
The questions that keep coming back on WhatsApp get their answer without tying anyone up, and your team keeps its time for the requests that matter.
A human stays in control
The bot sorts and prepares; it does not decide for you: the steps that commit you are validated with one button.
A record of every exchange
Everything is logged and linked to your CRM: you know who asked for what, when, and what came of it.
A predictable cost
Without AI, the bot costs its hosting, and on WhatsApp the messages Meta charges for, estimated at scoping. With AI answers, each message goes to the cheapest model that does the job, and spending is measured and capped: no nasty surprise on the bill.
Who it is for
- Your field teams jot down expenses, readings and requests on scraps of paper, and everything gets copied out later.
- Your customer service answers the same questions on WhatsApp every day.
- You want to receive your alerts where you already read your messages, not in yet another tool.
What you receive
- Your Telegram or WhatsApp bot, configured and verified.
- The connection to your CRM or your database.
- Your data-entry or answer scenarios, with human validation where it matters.
- AI answers drawn from your knowledge base, as an option.
- A conversation dashboard.
- Documentation for what comes next.
How it goes
-
Scoping
We first look at the tools you already use, what connects to them and the messaging app your team really uses, then together we choose the three scenarios that save you the most.
-
Build
We build the bot and connect it to your tools.
-
Test
Two or three of your users try it in real conditions.
Go-live
The whole team adopts it, and we adjust based on real conversations.
Frequently asked questions
Telegram or WhatsApp?
Telegram for your team: simple, reliable and with no platform fees. WhatsApp for your customers, with Meta’s rules: a number connected to its platform, which can stay the one you use in the WhatsApp Business app, and approved message templates, which we set up for you.
What does WhatsApp cost to run?
Meta charges for each message your bot delivers, by category and by the customer’s country, except in two cases: the first 1,000 replies of the month, for each number, and the window that opens when a customer writes to you from an ad leading to WhatsApp. Your customers’ messages are never charged. We estimate your volume during scoping: you know the running cost before the bot goes live.
Does the bot replace a person?
It replaces data entry and sorting, not judgement. Your team spends less time copying and stays in control of decisions.
Can the bot chain several steps, like an AI agent?
Yes, when a request cannot be settled in a single step. The bot then works in a loop: it plans, acts, checks its result and starts again until the goal is reached. We cap its number of turns, limit its rights to the planned scenario, and anything that commits the company (a refund, a quote, a booking) waits for a person to validate it. Otherwise, a fixed sequence is enough, safer and cheaper.
Why several AI models rather than one?
Because a message does not always need the same one, and the price follows the model. A small model works out what the person wants and files the request, a model good at extraction reads the photographed receipt, and only a hard question goes up to the most powerful one. An answer already given comes back from the cache instead of being paid for again. It is the method we applied on Palmora Property, a real-estate portal in six languages: switching to a suitable AI model divided the translation cost by 60, and 95% of segments come from the cache.
What about compliance?
Exchanges are logged, personal data is masked in the logs, and consent is handled on the WhatsApp side as Meta requires.
Rarely just one service. Most of our clients combine several: build your cart and ask for a bundled quote, a set of services gets a better price.
Build a bundled quoteGo further on this topic
Business process automation and bots with n8n
AI voice agents on the phone: what they can do in 2026
A voice agent picks up, understands a spoken request and answers with a synthetic voice, connected to your phone system. What it does well in 2026, what it does badly, the rules to follow, and the place of the people who answer the phone.
Will AI take young people's first jobs?
No disruption is visible across the labour market as a whole, but a signal appears among young people, in the occupations where AI replaces the task. What the studies say, our view, and the real question for an SME: how to train its juniors tomorrow.
Automate customer support: AI sorts, humans review
Incoming tickets and emails read, sorted and prepared by AI, then reviewed by your team when the reply commits the company: how to split the work, what can go out on its own, and why sorting costs a few cents when each step has the right model.
Go further on this topic
Business AI: private and at the right cost
Agentic AI: how an agent's loop works
An AI agent does not do everything in one go: it runs in a loop, gathers context, acts, checks and starts again. Understanding that loop means knowing where to put the controls, the limits and the human review.
The cost of AI in business: tokens, routing and forecasting
What you really pay when you use an AI through an API: input and output tokens, the context sent back with every call, an agent's turns. And a method to forecast the bill before you receive it.
20-minute diagnostic
Twenty minutes on a call, two or three concrete leads, no strings attached.
We look at your situation, identify what can be automated or improved, and tell you plainly whether we can help.