Automation

n8n automation, with or without AI: less manual re-keying

We start with the manual task that costs you most: within two weeks, it runs on its own, in production. The project then carries on with you, process by process, fitted to your organisation, your tools and your constraints. AI only comes in at the steps where a rule is not enough, and you know at all times what the automation costs you.

n8n, what is it?

n8n is automation software whose code is public, published by a Berlin-based company. You draw a process as a diagram: each box is a step (an email received, a record created in the CRM, a message sent), and the links say in which order they follow one another.

It connects to hundreds of off-the-shelf tools, from the CRM to invoicing, messaging apps and spreadsheets, and to the API of those without a ready-made connector. It runs on your server or ours: your data does not go through a third-party service, and the bill does not climb with the number of operations.

AI is one box among others. We place it at the step that needs it, and only there: the rest of the diagram stays made of rules, faster, cheaper and always the same.

A request arrives by email. Jev files it, a rule creates the quote in the CRM, a language model drafts the reply to a complaint, and a person decides as soon as the model hesitates.

A contact fills in the site form. A rule creates their record, Jev compares them with your ideal customer, and the sales rep is only called for priority contacts; the others get an email sequence.

A supplier invoice arrives. A language model reads it, the code compares it with the purchase order, and only a mismatch needs a person to look.

An order is confirmed. Invoice, payment check, shipping or reminder: everything follows rules, with no call to a model. Many processes look like this one.

A request written in free form. The agent searches over several rounds, with its model, its memory and its tools, but every action goes through Jev before it leaves, and anything risky waits for a person.

Swipe to follow the diagram

Rule, no AI
Decision model
Language model or agent
Person

It connects to your tools

A few of the tools n8n links, among hundreds of connectors. For the others, it goes through their API.

Twenty Odoo Dolibarr HubSpot Shopify Stripe Gmail Outlook Google Sheets Excel Notion Airtable

Slack Microsoft Teams Telegram WhatsApp PostgreSQL Supabase Jev Clef Mistral Claude Qwen Webhooks et API

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.

73%

of French companies that use AI use it to optimise costs (time saved, automation of repetitive tasks), and 64% for more reliable processes.

Source: INSEE, Insee Première No. 2120, 21 July 2026

2025 survey of 11,000 companies with 10 or more people, on their organised use of AI.

11%

of French small and medium-sized businesses use AI to automate tasks, 6 points more in a year, against 34% to generate text, voice or images.

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.

What you gain

Time given back to your teams

No more copy-pasting from one tool to another. Your teams focus on the work that really needs a person.

Fewer data-entry errors

Information entered once reaches everywhere it is needed, with no typos or omissions.

No silent failures

If something gets stuck, you are alerted and the work resumes where it stopped. Nothing is lost along the way.

A known, controlled cost

You see what each run and each month costs. No per-operation bill that climbs with your activity.

Your data stays with you

The automation runs on your server or ours, not with a third-party service that bills by usage.

A risk-free transition

The old way of working remains available until the new one has proven itself.

Fitted to your company, not to a template

The same process is not automated the same way in a team of 20 people and in a group of 500. Before building, we look at your structure, the way you work, your environment and your constraints. In practice, this is what it covers.

How your data is handled

Where it lives, what may leave the company and what must not, what the GDPR and your contracts require. That decides where the automation runs and which AI model is allowed to touch it.

Your internal policy on tools

The software you allow, whether AI may be used and by whom, the approvals required before an action goes out. The automation applies these rules instead of getting around them.

Your business software

Your ERP, your CRM, your production tool or your in-house software, with or without an API, and the Excel files that link them. We start from what is in place rather than making you change tools.

The resources available

Who does the task today, the time the team can give the project, who will look after the automations day to day, and the monthly budget you accept for AI.

Your organisation

Your departments, your sites, your approval chains and your peaks of activity. An automation follows the way your company makes decisions, not a generic diagram.

Your environment

Your customers, your suppliers and the formats they send you, your working languages, the obligations of your sector and the security rules of your network.

Who it is for

Your team copies orders, requests or invoices from one tool into another.
You want a digest every morning without anyone spending time preparing it.
Your CRM, your invoicing and your messaging do not talk to each other.
Your teams sort emails, requests or files by hand every day.
You want AI in your processes, but only where it brings in more than it costs.

What you receive

A first process automated end to end, in production.
The list of the next processes, ranked by what they bring you.
Alerts if something gets stuck, and a log of every run.
A meter showing the cost per run and per month.
For each step, the written choice between a rule, an AI model or a person, and what it costs.
Clear documentation and your team trained.
Monitoring and fixes for at least 3 months (€350/month), with a checkpoint at 30 days.

Prerequisites

For a process to hold up in production, you need:

Tools that open up through an API, a webhook or a scheduled export.
A business owner who signs off on the expected result.
A service account in your name for each connected tool.

How it goes

Scoping
We watch the task with the person who does it today, and your situation around it: your data, your internal rules, your business software, what the team is ready to change. For each step, we decide whether a rule is enough or whether AI brings in more than it costs.
Build
We build the automation and test it on your data.
Go-live
It takes over gradually, with the old way kept as a fallback.
Ongoing
Alerts in place, monitoring and fixes for at least 3 months, a checkpoint at 30 days. Then we move on to the next process, in order of what it brings you, and adjust the ones already running when your organisation or your tools change.

With or without AI: six example workflows

Without AI: the quote request filed and assigned

The form on your site creates the record in the CRM, assigns it to the sales rep for the area based on the postcode and alerts management above a certain budget. The fields are already structured: a rule is enough, with no paid call to a model and the same result every time.

Without AI: the order followed end to end

A confirmed order creates the invoice, updates the stock and the customer record, then reminds the customer if the payment does not arrive. Nothing to interpret, so nothing to hand to AI: a fixed sequence, cheaper and safer.

With Jev: the inbox sorted

Each incoming email is filed (quote, complaint, invoice, urgent) by a decision model such as Jev, from TypeSafe AI. It writes nothing: it picks from a closed list and says how sure it is. Above the threshold, the workflow passes it to the right team; below it, a person decides.

With Jev: the prospect compared with your ideal customer

A new contact comes in through the site or a trade show: the decision model compares it with your ideal customer, spots buying intent and sets its priority. Your sales reps start their day with the contacts that matter, and keep the first conversation and the negotiation.

With a language model: the supplier invoice read and matched

The PDF received is read, its references and amounts are extracted, then the workflow compares them with the purchase order. The arithmetic stays with the code, which does not get sums wrong: a mismatch goes to review instead of being paid.

With a person: the decision that commits you

An off-grid discount, a refund, anything that affects an employee or a candidate: the workflow prepares the file, and a person approves in one click from their messaging app. AI can sort and prepare, never decide alone about a person.

Frequently asked questions

What makes the price of a process vary?

Three things: how many tools to connect, how good their APIs are, and how many edge cases to handle. A flow between two well-opened tools stays within the base package; a tool without an API or many business rules take more work, and we quote it before we start.

Why n8n rather than Make or Zapier?

n8n runs on your side: no per-operation bill that explodes with volume, and your data remains yours. It is our default choice, not an exclusivity.

What happens if the automation goes down?

You are alerted, and it resumes where it stopped. An automation that fails silently is worse than a manual task, so we do not deliver one that way.

What is the minimum commitment?

A first process in production, with its alerts and its cost meter, then 3 months of monitoring and fixes at €350/month. That is the period when a workflow meets the real cases no test had foreseen, and when we adjust it. After that, monitoring continues month to month, and you decide process by process what comes next and at what pace.

What if we have five processes to automate?

It is the most common case, and that is why the offer is an ongoing project. We start with the one that costs you most, get it running, then move on to the next. When everything seems worth automating, the Audit Sprint first reviews your processes, your tools and the people who use them: it tells you in which order to proceed, what the team needs to learn, and what is not worth automating.

Do you need AI to automate?

Often not. Most processes follow simple rules: this field filled in, that action. AI comes in where a rule is no longer enough, such as reading an invoice or sorting a request, and we combine several models, each on the task it does well at the lowest cost, with a cache so that the same answer is never paid for twice. On Palmora Property, switching to an AI model divided the translation cost by 60, and a cache serves 95% of segments without calling the model again.

What does a decision model such as Jev bring?

Many decisions in a process need no sentence at all: filing an email, judging whether an action is risky, choosing the team that will handle a request. A decision model such as Jev, from TypeSafe AI, or Clef, from Cloudflare, answers them with a choice from a closed list and a probability, faster and far more cheaply than a large model used for sorting. We first test it on your own cases, it then works alongside the team without acting, and the threshold that lets it act alone is set on what it has shown. Jev is a young service hosted in the United States: the decision therefore goes through your own entry point, and switching to Clef, whose open weights install on your side, remains a configuration change.

What about an AI agent in the automation?

Only when the path cannot be planned in advance, for example a free-form request that must be understood before it is filed in the right place. The agent then runs in a loop: it acts, checks its result and starts again until it reaches the goal. In n8n, we cap its number of rounds, limit its permissions to what it needs, have a decision model judge each sensitive action before it goes out, and have a person approve anything that commits the company. The rest of the process remains a fixed sequence, safer and cheaper.

Go 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.

All articles: Business process automation and bots with n8n