Knowledge sources
We select the documents and systems the assistant will answer from and check that they are current and that access rights are correct. What the assistant must not touch is defined from the start.
An assistant that knows your policies, price lists and contracts, not the internet. We deploy ChatGPT assistants for employees and customers with your company knowledge, access rules and a clear answer on where each piece of information came from.
Built for ISO 27001NIS2 DORA
A general chatbot gives polished answers, but it does not know your leave policy, what your service costs or what your contract with a customer says. A company assistant should answer from your documents, see only what the employee asking is allowed to see, and cite its source so the answer can be checked.
We build ChatGPT assistants as Custom GPTs in a company workspace with your documents, projects and connections to SharePoint or Google Drive. We connect the knowledge sources (policies, price lists, product descriptions, contract templates) using your existing access rights, set the tone and the limits (what the assistant must not do), and measure how many questions are answered without a human.
The scenarios we implement most often with ChatGPT. Each one starts with a single process and is measured.
From the first conversation to a working solution, with measurement and ongoing support.
We select the documents and systems the assistant will answer from and check that they are current and that access rights are correct. What the assistant must not touch is defined from the start.
We build the assistant as a Custom GPT in a company workspace with your documents, projects and connections to SharePoint or Google Drive, and set the tone, language, limits and the requirement to cite a source.
A pilot group asks real questions for two weeks. We measure how many are answered correctly and without a human, and fix gaps in the knowledge.
We launch to everyone, track unanswered questions and refresh the knowledge sources every month.
No more than the employee asking could see directly: the assistant works within existing access rights. ChatGPT Business, Enterprise and API data are not used to train models, and the company workspace is controlled by an administrator: who signs in, who sees what, which settings are enabled.
It says it does not know and points the user to a person. We set this in the rules. We review unanswered questions and add to the knowledge sources.
Yes. Typically there are separate assistants for sales, HR and customers, because knowledge sources and tone differ. We start with one.
Pricing is per user (ChatGPT Business / Enterprise) or by usage (API); we choose the mix based on what is actually used. We give the implementation price after the first conversation.
We automate what repeats: invoices, orders, reports, contract review.
An agent is not a chat window but a coworker without hands: it receives a task, gathers data from your systems, takes action and reports back.
AI is most useful not in a separate window but inside your systems: ERP, CRM, helpdesk, document management.
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
AI systems are deployed with protection against data leakage and model abuse.
The AI security programme and its controls are managed following the ISACA methodology.
Personal data is handled according to privacy by design and GDPR requirements.
We reply within 1 business day