Copilot Comptable
The AI copilot for Swiss accounting firms. It reads the firm's inbox, replies to clients drawing on the full history of the file, classifies, renames and files every incoming document, then books it. Sovereign: open-source LLMs self-hosted on OVH, no data ever leaves Europe.
Private demo
This client project is confidential. The screenshots above are shared with client approval.
// recruiter view
The AI copilot for Swiss accounting firms, built around a clearly identified market need: firms still spend hours a day classifying, sorting, reading and re-typing accounting documents, and hand-replying to every client email — without being able to lean on US-based AI SaaS due to FADP. Backend, AI engine and deployment carried end-to-end, in direct partnership with the pilot firm, with a multi-tenant SaaS ambition at the end.
- ▸Sorting, classification, reading and key-data extraction now automatic across 9 document types — no more hours spent every day classifying and re-typing what landed in the firm's inbox
- ▸Client emails handled automatically: the AI reads the entire thread history and every attachment to draft acknowledgements, reminders and error reports
- ▸Multi-tenant SaaS with three roles (client, staff, admin), plus tax, VAT and HR assistance
- ▸Several hours of manual entry saved every day for accountants at the client firm
- ▸Sovereign AI choice (self-hosted Llama 3.2 Vision on OVH) to tick GDPR + FADP — a decisive argument for the firm
- ▸Designed from day one as a commercial product: multi-tenant SaaS or on-premise license for the French- and German-speaking Swiss market
The story behind
- Chapter 01
The product
Copilot Comptable was designed and shipped within MapBrain for Swiss accounting firms: I own the architecture, the AI engine, the backend and the deployment, working in direct partnership with the pilot firm. One clear goal — take the data-entry workload off the accountants' desk and ship it to production.
- Chapter 02
The trigger
The pilot firm was spending several hours a day manually re-typing PDF invoices into Cresus. Swiss accounting tools offer almost no AI automation, and entrusting client data to a non-European SaaS was unthinkable from a FADP compliance standpoint.
- Chapter 03
Technical choices
Instead of an OpenAI API call, I chose self-hosted Llama 3.2 Vision on a dedicated OVH server: data 100% in Europe, controlled costs, zero third-party dependency. Async FastAPI + Celery to digest batches of files, Alembic for zero-downtime migrations, Fernet encryption on all sensitive data.
- Chapter 04
The obstacles
First obstacle: the model was hallucinating amounts because of the Swiss format (apostrophe as thousands separator, VAT 8.1%/2.6%/3.8%, QR-invoices). Solution: strict JSON mode + few-shot prompts specialized on Swiss documents. Second obstacle: Gmail/Outlook threads sometimes hide attachments inside nested messages — full rewrite of the IMAP parser.
- Chapter 05
Going to production
Progressive rollout rather than a big bang: first classification in read-only, then automatic acknowledgement emails, finally direct export to Cresus. Each step validated by a human accountant before activating the next — zero regressions, gradual trust.
- Chapter 06
What's next? Toward a SaaS
Beyond its current usage, the product answers a market need that goes well beyond any single client: nobody today offers Swiss accounting firms sovereign AI automation for accounting entry. The logical next step — package the whole thing as a multi-tenant SaaS (or as an on-premise license for firms with the strictest data requirements) and open it up to the entire French- and German-speaking Swiss market.
After going live
Monitoring & observability
Full observability stack to monitor the AI pipeline and email automation in production, with alerting on vision model drift and OAuth2 errors.
Stack
Tracked metrics
- ●Ollama Vision latency (p50 / p95)
- ●Classification accuracy per document type
- ●Celery queue depth and per-batch processing time
- ●OAuth2 error rate for Gmail / Outlook / Bexio
- ●OVH Swift storage consumed
- ●Sentry alerts on LLM hallucinations and timeouts
Production impact
Deployed as a pilot at the client firm, the system now absorbs the data-entry tasks that used to dominate accountants' daily work.
- ▸Manual entry replaced on the 9 most frequent document types (invoices, statements, expenses, contracts…)
- ▸Acknowledgements and reminders sent automatically — no more forgotten follow-ups
- ▸FADP + GDPR compliance maintained: AES-encrypted data, European hosting, zero external API
- ▸Automatic detection of Swiss VAT rates (8.1% / 2.6% / 3.8%) — entry errors eliminated
- ▸User feedback: accountants refocused on client advisory work rather than repetitive entry
// results
// stack