We sell AI in production, not demonstrations
Between the POC that impresses a steering committee and the system that holds up in production, the gap is enormous: evaluation, guardrails, observability, cost per request, data governance. Most AI projects die in that gap. We know it because we crossed it for our own products: ComptaIA, our AI pre-accounting product, runs with more than twenty clients; the analytical-review assistant in HOLOS is used by audit firms on real engagement files. Proof through our products, not through our slides.
That experience has also taught us to say no. A use case with no exploitable data, no measurable ROI, or one that a business rule solves better than a model will not get past the framing note — and that note will tell you so plainly. For organisations whose data cannot leave the country, we deploy self-hosted open-source models; sovereignty is not a marketing option, it is an architectural constraint we know how to hold.
Use cases we operate
Business copilots
- Accounting: an assistant that proposes postings, generates supporting documents, prepares tax filings
- Audit: assisted analytical review, working-paper generation, synthesis of complex documents
- Legal: contract analysis, clause extraction, version comparison
Structured extraction (OCR + LLM)
An OCR + LLM pipeline extracting structured fields from complex documents: invoices, contracts, reports, handwritten forms. Human-in-the-loop validation for contentious cases.
RAG (Retrieval-Augmented Generation)
Internal knowledge bases searchable in natural language: documentation, case law, standards, procedures. Embedding, semantic search, contextual generation.
Conversational automation
Message-triggered workflows (Slack, Teams, WhatsApp Business) with tool-calling on your internal systems: create a ticket, schedule a meeting, launch a report.
Technical stack
- LLMs: Claude (Anthropic API and SDK) as the foundation; OpenAI and open-source models (Ollama / vLLM) where the use case or a sovereignty constraint requires it
- Frameworks: LangChain, LlamaIndex, custom orchestrators
- OCR: Mistral OCR, Tesseract, AWS Textract depending on the case
- Vector DB: Pinecone, Qdrant, pgvector
- Observability: LangSmith, Langfuse, custom logging