AI for accounting firms in Switzerland

What AI can do in an accounting firm

In an accounting or fiduciary firm (a fiduciaire, in French-speaking Switzerland), much of the time goes into what surrounds the accounting: chasing documents, renaming and filing them, keying in amounts and answering the same client questions. The load peaks early in the year, when year-end closings and tax returns arrive at once.

Industry AI tools such as TreuhandGPT help your staff; we automate the document and email flows around your accounting software. Documents that arrive by email or upload are sorted and filed, and their key figures extracted. A checklist for each client shows what is missing, and the reminders are ready to go.

Nothing goes out without your say-so: the agent prepares, your team approves, and you choose where the data is processed. To get started, half a day of AI training helps your team use AI without exposing client data.

The problem

Where the time goes today

Documents arrive from everywhere

Email, phone photos, post, upload portals: every client sends documents their own way, and everything is sorted and keyed in by hand.

Endless reminders

There is always a bank statement, a salary certificate or a pillar 3a statement missing. Reminders go out client by client, and the file waits.

The early-year peak

Year-end closings and tax returns overlap, and the same questions keep coming: ‘What do I need to send you?’, ‘Where is my tax return?’

Interactive demo

Try the agent on an accounting document

Pick a fictional document (a supplier invoice with a Swiss QR-bill, a bank statement…) or paste your own text. The agent extracts the fields, then plain code with no AI re-checks them: IBAN checksum, VAT at 8.1% recalculated, totals. It then proposes an accounting entry or lists the missing documents.

Document reading agent

Reads invoices, statements and applications. Code re-checks every franc. You approve.

Idle

Where does the AI run?

agent · document reading Fictional data

Fictional document, in French as is common in Romandy

releve-2026-10.pdf e-banking · Banque Démo SA waiting

Imprimerie Calame Sàrl
Rue de l’Exemple 5
1000 Lausanne
CHE-123.456.789 TVA

Alvélia Fiduciaire Sàrl
Chemin des Démos 12
1200 Genève

Facture n° 2026-1187

Lausanne, le 30.10.2026 · Conditions : 30 jours net

Désignation	Qté	Prix	Montant
Flyers A5, recto-verso	2’000	0.34	680.00
Affiches A2	50	8.40	420.00
Mise en page et préparation	1	140.00	140.00
Sous-total HT			1’240.00
TVA 8,1 %			100.44
Total CHF			1’340.44

Section paiement

Compte / Payable à
CH44 3199 9123 0008 8901 2
Imprimerie Calame Sàrl

Référence
21 00000 00003 13947 14300 09017

Monnaie CHF · Montant 1’340.44

Banque Démo SA

Relevé de compte courant · Alvélia Fiduciaire Sàrl
IBAN CH93 0076 2011 6238 5295 7 · 01.10.2026 – 31.10.2026

Date	Libellé	Débit	Crédit
	Solde initial		24’310.55
02.10	Paiement QR, Favre & Fils (réf. …0417)		2’160.00
05.10	Loyer bureau octobre	2’450.00
09.10	Paiement QR, C. Rochat (réf. …0422)		540.00
14.10	Télécom Démo SA, facture mensuelle	189.90
20.10	Virement, Atelier Nivéo Sàrl		1’296.80
27.10	Salaires octobre	18’430.00
29.10	Virement, J. MARTIN		800.00
	Solde final		8’037.45

›

Extracted data AI

Run the agent to read this document.

Checks done by code Code

Code will redo every calculation, no AI involved.

Try it with your own text

Everything runs in your browser: nothing is sent or stored. Simplified demo: answers are prepared in advance or computed by simple rules in your browser. In production, a language model suited to your data does this work, and someone on your team signs off.

I want this for my business

What’s happening, step by step

The document arrives Input

A PDF invoice by email, a scan, a photo or a bank statement: the agent picks it up wherever it lands, like a colleague opening the post.
The AI reads the page AI

It reads the text and understands the layout: where the supplier, the lines, the total and the payment part are.
It pulls out the fields AI

Supplier, number, dates, amounts, IBAN, QR reference: each value goes into its own box, ready to be checked.
Code checks every figure Code

No AI here: plain code redoes the maths (IBAN checksum, QR reference, VAT at 8.1%, totals). If an amount was misread, the sums don’t add up and the document is blocked.
A proposal is ready Output

An accounting entry, a bank reconciliation or a list of missing documents with the reminder drafted: the work is prepared, not yet carried out.
You approve Human

Nothing is imported or sent without your go-ahead: you check at a glance, correct if needed and approve.

Run the demo: each step lights up here.

ModelOpen-source OCR + Apertus 70B

Data processedA server in Switzerland or yours

Picture a colleague who opens every invoice, statement or application the moment it arrives, copies the right details into the right place and redoes every calculation before showing it to you. It never tires, and you always have the final say.

example 9 checks done by code, not AI, on the demo invoice

example 5 min → 20 s to key in and check a supplier invoice

example 0 entries imported without your approval

Words to know

Multimodal model: An AI model that also reads images: PDFs, scans, photos. It understands the layout, not just the words.
QR-bill: The Swiss invoice with a payment part and a QR code, which replaced the old payment slips. It carries the IBAN, the amount and a reference that can be checked.
Checksum: A digit calculated from the others. If a single digit of an IBAN is wrong, the sum no longer works out, so the error is caught.

Why it’s safe

Code recomputes amounts, VAT, IBAN and QR reference: no figure is guessed by the AI.
A single failed check blocks the document until a person looks at it.
The agent prepares entries and reminders: it pays nothing and sends nothing without your approval.
You choose where the AI runs and where your data is processed.

The agent’s pipeline

Input Intake A dedicated email address, shared folder, scanner or upload. Each new file starts the pipeline.
AI Reading and extraction A multimodal model, or OCR then a language model. Schema-validated JSON: fields, lines, amounts.
Code Checks IBAN (mod 97), QR-IBAN, QR reference (mod 10), VAT at 8.1% recomputed, totals, due date, duplicates.
Code Business rules Your chart of accounts: supplier → expense account, VAT code, matching by QR reference.
Human Approval An approval queue: anomalies come first, you correct or approve.
Output Export Clean data, ready to import into your accounting software: file, API or email.

AI reads and writes. Code checks. Humans decide.

Stack

n8nPythonOpen-source OCRApertus · GPT · Claude · Gemini · MistralJSON SchemaQR-bill · camt.053PostgreSQL (audit log)

Guardrails

Code checks, not AI: amounts, VAT, IBAN and QR reference are recomputed. A single failed check blocks the document.
Structured output: the model’s answer must match a JSON schema; if it doesn’t, the document goes to a person.
IBAN changes flagged: if a known supplier’s bank details change, a person must confirm (a classic invoice fraud).
Nothing goes out on its own: the agent prepares entries and reminders; it never pays or sends anything without approval. Every step is logged.

What the agent produces (JSON)

{
  "document": "facture-2026-1187.pdf",
  "type": "supplier_invoice",
  "supplier": {
    "name": "Imprimerie Calame Sàrl",
    "vat_id": "CHE-123.456.789"
  },
  "number": "2026-1187",
  "date": "2026-10-30",
  "due_date": "2026-11-29",
  "amounts": {
    "currency": "CHF",
    "subtotal": 1240,
    "vat_rate": 8.1,
    "vat": 100.44,
    "total": 1340.44
  },
  "payment": {
    "qr_iban": "CH4431999123000889012",
    "reference": "210000000003139471430009017"
  },
  "checks": {
    "passed": 9,
    "failed": 0,
    "iban_mod97": true,
    "qr_reference_mod10": true,
    "vat_recomputed": true,
    "totals_match": true
  },
  "proposal": {
    "debit": "6600 Advertising",
    "input_vat": "1171 Input VAT",
    "credit": "2000 Accounts payable"
  },
  "status": "awaiting_approval"
}

Choose the engine

How we set it up

Day 1 Free audit 30 minutes to go through your document types, your volumes and your accounting software.
Weeks 1–2 Test on your documents We test the reading and the checks on a sample of your real documents and measure the quality field by field.
Weeks 2–4 Go-live We aim for a first automation in service 2 to 4 weeks after the audit, connected to your mailbox or shared folder.
Every month Care Monitoring, new suppliers and document types, and a monthly report.

What we need from you

A sample of your documents (invoices, statements, applications), anonymised if you prefer
Your chart of accounts and booking rules
The email address or folder where your documents arrive

I want this agent

What we set up

The flows around your accounting software

Three automations to start with, built on your document types and your approval rules.

01

Document intake

Documents that arrive by email or upload are sorted, renamed and filed by client. Amount, date, VAT and IBAN are extracted and re-checked.

SortingExtraction

02

Missing-document reminders

A checklist per client shows what is missing. Reminders are prepared; you decide whether they go out after approval or automatically.

ChecklistReminders

03

Client email sorting

Each email is labelled and passed to the right person, with a draft reply for routine questions. See email triage.

DraftsHuman approval

04

Data ready to import

Extracted figures and proposed entries: clean data, ready to import into your accounting software.

05

Team training

A half-day workshop: using AI safely and writing your AI usage policy. See the training.

06

Monthly care

Hosting, monitoring, adjustments before tax season and a report every month.

How we work

How it goes

Free audit

In 30 minutes we review your documents, reminders and email.
Team workshop

If you wish, half a day to train the team and choose the first automation.
Test on your documents

We test on a sample of your documents, for example last year’s, before go-live.
Go-live and care

We aim for a first automation in service 2 to 4 weeks after the audit, then fine-tune it every month.

Our commitments

Client data stays under your control

A human approves

By default, nothing is sent without approval. You choose, case by case, what may go out automatically.

You choose where data is processed

Leading models or, for sensitive data, open-source models such as Apertus, the open Swiss language model, hosted in Switzerland or on your own servers.

Built with Swiss data protection (FADP) in mind

A data processing agreement (Art. 9 FADP), only the data the task needs, Swiss hosting available.

Frequently asked questions

How do you protect our clients’ confidential data?

You decide where it is processed, and only the data the task needs is sent. A data processing agreement covers the processing. For sensitive files, Apertus, the open Swiss language model built by EPFL, ETH Zurich and CSCS, can be hosted in Switzerland or on your own infrastructure.

Do we need to change our accounting software?

No. We deliver clean data, ready to import into your accounting software, and connect the tools you already use (email, Microsoft 365 or Google Workspace, your business software) through their API, an export or email.

Do reminders go out to our clients on their own?

Only if you say so. By default, your team approves each reminder; you can allow automatic sending for simple reminders and stop it at any time.

Do you offer AI training for accounting firms?

Yes, a half-day workshop at your office, with examples from your own work: using AI without exposing client data and writing your AI usage policy. See AI training and our policy template.

How long does it take to set up?

We aim for a first automation in service 2 to 4 weeks after the audit. Because we can test on last year’s documents, you can start outside the busy season.

How much does it cost?

On quote, depending on your document volumes and the tools to connect. The audit is free; you then get a clear quote with a set-up cost and a monthly fee. Request a quote.

NotHuman

How many hours does your team spend chasing documents?

In a free 30-minute audit, we pinpoint the flows to automate first and propose a concrete plan.

Book my free AI audit Write to us

AI for accounting firms in Switzerland: less data entry, more time for clients

What AI can do in an accounting firm

Where the time goes today

Documents arrive from everywhere

Endless reminders

The early-year peak

Try the agent on an accounting document

Document reading agent

The flows around your accounting software

Document intake

Missing-document reminders

Client email sorting

Data ready to import

Team training

Monthly care

How it goes

Free audit

Team workshop

Test on your documents

Go-live and care

Client data stays under your control

A human approves

You choose where data is processed

Built with Swiss data protection (FADP) in mind

Frequently asked questions

How many hours does your team spend chasing documents?

A question? A project?

Thank you, it’s on its way.

AI for accounting firms in Switzerland: less data entry, more time for clients

What AI can do in an accounting firm

Where the time goes today

Documents arrive from everywhere

Endless reminders

The early-year peak

Try the agent on an accounting document

The flows around your accounting software

Document intake

Missing-document reminders

Client email sorting

Data ready to import

Team training

Monthly care

How it goes

Free audit

Team workshop

Test on your documents

Go-live and care

Client data stays under your control

A human approves

You choose where data is processed

Built with Swiss data protection (FADP) in mind

Frequently asked questions

Read next

How many hours does your team spend chasing documents?