Website
Your site on our technology
A website for your firm on the same technical foundation as innovorsorge.ch, with a blog, two languages and embedded calculators.
AI that runs in your office
We supply and run a server on which the language model and text recognition work locally. Client documents do not leave your office network and are not sent to OpenAI, Anthropic or any other provider.
What you get
Hardware and software as a ready-to-use package. You need neither server know-how nor your own IT department.
01
Local server
A device in your office, designed for working with language models. We deliver it set up.
02
Open language models
Models with open weights that run without a connection to a provider. We choose with you which model is used for what.
03
Offline text recognition
Scanned certificates, policies and tax documents are converted locally into searchable text.
04
Redaction
The language model suggests names, addresses, AHV numbers and IBANs for redaction. You review and confirm.
05
Connection to the hub
With the Hub module you use the local AI directly from your cases.
06
Maintenance
We install updates to models and software as agreed with you.
Where your data is processed
Everything that happens to client documents stays inside your office network. It needs no outside connection.
Office network diagram
- Upload document
- Recognise and process locally
- Result in the case
Your office network
Workstations
Workstation 1
Workstation 2
Local server
- Open language model
- Offline text recognition
- Redaction
Case storage
Outside
AI providers in the cloud
No transfer of client documents
The AI suggests, you decide
Even locally, the AI remains a tool that does the groundwork. You see what it suggests before anything happens with it.
Tap or hover over a role to see its tasks.
We set up the infrastructure, operate and maintain it. When your firm has a specific request, we build the solution for it.
- Set-up of hub, website or local server
- Operation, updates and backups
- Maintenance and support
- Further development on specific request
New report template built on request
You decide what the calculations are based on and how texts are written, and what goes to the client. The client relationship stays with you.
- Set assumptions, templates and tone
- Review suggestions and drafts
- Decide and approve
- Lead conversations and the client relationship
Report moved from draft to approved
The AI reads documents, recognises client data and drafts texts. What it delivers remains a suggestion until you approve it.
- Read and file documents
- Suggest client data for redaction
- Draft report texts in your tone
Suggestion: redact 4 items
Figures come from fixed calculation methods, not from the language model. The same inputs give the same result, the workings are in the appendix.
- Asset projections and pension gaps
- Tax effect of buy-ins and pillar 3a
- Overlaps and concentrations in portfolios
- Workings to read through
Same inputs, same result
How the introduction works
Assessment
We clarify which tasks should run locally and how your office network is set up.
Delivery and set-up
We deliver the server set up, connect it and test the workflows with sample documents.
Training and operation
You and your team learn the workflows on your own documents. After that we take care of maintenance.
The costs
We do not bill by the hour but like subscription software: once for the set-up, then on an ongoing basis for operation and development. We set the price after the first conversation, because it depends on the scope.
Price on request: a one-off set-up and an ongoing fee.
- One-off set-up
- Server, set-up of language model, text recognition and redaction, connection to your office network and training.
- Ongoing fee
- Maintenance, updates to models and software and new workflows we develop for our own company.
Frequently asked questions
Does the server need an internet connection?
Not for processing client documents. For updates we connect it as agreed with you, no client data is transferred in the process.
Are local language models as good as the well-known cloud services?
For tasks such as text recognition, redaction, summarising and structuring documents they are sufficient in daily work, based on our experience in our own company. For calculations we use fixed methods anyway.
Which hardware and which models do you use?
That depends on your workflows and the number of workstations. We put the equipment together in conversation with you and explain what is used for what.
What happens if the server fails?
We get in touch with you and fix the problem, on site if needed. The website and tools for your clients keep running independently.
The other four modules
Each module can be used on its own or combined with the others.
Tools
Calculators and tests for your clients
Calculators and tests for your clients, such as a compound interest calculator, budget calculator, pension fund test or retirement self-test.
Hub
All tools in one workflow
Cases, reports, redaction, portfolio analysis and documents in one place, set up around your workflow. Provided with a one-off set-up and an ongoing fee.
Custom
Whatever else you need
Whatever does not fit into one of the modules, we build with you as a dedicated solution.
See the module in a demo
We show you the module on sample cases and clarify which parts fit your firm.
Price on request: a one-off set-up and an ongoing fee.