Skip to content

chifty Enterprise

On-premise AI for your company

Introduce chifty on your own infrastructure through an assisted pilot. Agree the products, model processing and operational responsibilities for your setup.

Your own infrastructure · Your own AI choice · Currently a pilot program

What does chifty On-Premise mean?

chifty runs in your environment. This does not automatically mean every connected service runs locally: email providers, model endpoints and optional functions need separate review. A local model configuration can be planned for a defined scope.

Define the operating scope

Choose the initial products, sources and roles. Your IT provides the agreed environment; the pilot defines setup assistance, acceptance criteria and responsibility for operation.

Backups, updates, monitoring and incident handling need an owner. Specify what your team handles and what support is agreed with chifty.

Separate the application from model processing

A locally hosted application can still send requests to an external model endpoint. Review model selection, routing, processing region and retention for each enabled task.

Fully local inference needs suitable models and hardware. Test quality and response times with the intended sources; do not assume that every optional function works offline.

Start with a measurable pilot

Use a bounded source set and representative tasks. Include permissions, source changes and questions without supporting information in acceptance testing.

Expansion follows the agreed review. Document which connectors, models and workflows were accepted and repeat relevant checks after changes.

How the rollout works

On-premise isn't a self-service download for us — it's a personally guided start.

  1. First conversation

    You reach out via our contact page. Together we work out whether and how on-premise fits your environment.

  2. Joint planning

    We go through the technical requirements and the setup process together with your IT team.

  3. Setup

    You set chifty up on-site, and we guide you through it and answer any questions along the way.

  4. Acceptance and operation

    Review the agreed tasks and assign owners for updates, sources and support.

Security isn't an add-on

Local AI, tenant isolation, access control, and concrete technical measures: find all the details on our security page.

Go to the security page

Frequently asked questions

Does on-premise mean all data stays local?
Only when the full configuration supports that requirement. Check model endpoints, email providers, connected sources and optional services separately.
Which hardware is required?
It depends on the source volume, active users, models and whether inference runs locally. Agree a target load and test a suitable configuration; the GPU calculator supports initial planning.
Who operates and updates the installation?
Define infrastructure, backups, updates and incident ownership before rollout. The pilot agreement sets out the assistance included from chifty.
Is a pilot an immediately available standard package?
The pilot is planned individually. Product scope, prerequisites, schedule and terms are agreed for your project.