AI that knows your company
Not a generic chatbot, but an assistant answering from your policies, contracts and data. With a link to the source, and a clear picture of who may ask what.
Why choose me?
What you get out of working together, beyond a working solution
Answers grounded in your documents
The AI draws on your policies, contracts and internal documentation. Every answer shows its source, so you can verify it.
Your documents stay with you
The application and the knowledge base run in your own cloud tenant or on-premise. The language model I call through a commercial API in a mode where the provider does not train on your content and does not retain it beyond serving the request, in an EU region and under a processing agreement.
Time saved looking for information
Employees stop spending hours searching shared drives and the intranet. They get an answer, with a link to the document, in seconds.
Connected to your business systems
Integration with SharePoint, DMS, databases or your internal portal. The AI works with current data, not a stale export.
Access control and audit trail
Users only see what they are authorised to see. Every query is logged, giving you both usage insight and an audit record.
Measurable benefit
Before we start, we define what the solution should improve. After deployment we measure whether it actually does, not just by gut feeling.
Types of solutions
Choose the solution that best fits your needs
Internal knowledge assistant
AI over your policies, documentation and knowledge base.
- Search across company documents
- Answers with source citations
- Role-based access
Customer support assistant
Support that answers faster and more consistently.
- Suggested replies for agents
- Helpdesk integration
- Analysis of frequent queries
Document and data processing
Extracting data from contracts, invoices and reports.
- Data extraction from documents
- Completeness checks
- Export into business systems
Where to find me and where I work from
I am based in Prague and in Tálín near Písek. Consultations run online or in person. I work with clients across the Czech Republic and abroad.
Prague
Letňany and surroundings
Tálín near Písek
South Bohemia
Online
Czech Republic and worldwide
Frequently asked questions
Answers to the questions clients ask most often
What is RAG and how does it differ from a normal chatbot?
RAG (Retrieval-Augmented Generation) means the model first retrieves relevant passages from your documents and only then formulates an answer over them. It does not rely on what it learned during training, it answers based on your data and can show the source.
Where will our data live?
Documents, the vector database and the application can run in your Azure tenant, a private cloud or on-premise. The language model itself is a commercial API (OpenAI, Anthropic, Google) called in a mode that does not train on your content, in an EU region and under a data processing agreement. So the model does not run on your premises, but it does not keep your data either. If you need the data never to leave your perimeter at all, I will tell you at the outset, because that is a different category of project.
How do you stop the AI from making things up?
Answers are tied to retrieved sources and every one carries a citation. If there is no supporting document, the assistant says so instead of inventing an answer. Quality is verified against a set of test questions before go-live.
What does it cost, and what about running costs?
The price depends on the volume of data and the number of integrations. Running costs are mainly model calls and hosting. I always include an estimate of the monthly run rate in the quote so you decide with the full picture.
How long does deployment take?
A pilot over a defined set of documents usually takes 3 to 6 weeks. A full rollout with integrations and role-based access control takes 2 to 4 months depending on scope.
How do you handle GDPR and personal data?
Personal data is addressed at design time, through source filtering, anonymisation and access control. I sign an NDA and hand over processing documentation for your internal audits.
Considering AI in your company?
In the initial consultation we go through your data, processes and risks and decide whether RAG makes sense in your situation, even if the answer turns out to be not yet. Remotely or in person (Prague, South Bohemia).
Before I build anything, we go through your processes and I write up where AI pays off, how much it saves and what running it will cost. The audit fee is deducted from the project that follows.
Or go back to the contact form