ZenAI knowledge base

ZenAI documentation

Setup, integration, and operations guides for the ZenAI on-premises inference and appliance-licensing platform — from provisioning an appliance to tuning inference for production workloads.

Getting started

First steps with ZenAI

Bring an appliance online, distribute models, and license node capacity before you put ZenAI into a production inference path.

Appliance Provisioning

Binding a ZenAI appliance to a subscription, configuring node-per-appliance licenses, and verifying activation.

Coming soon

Model Management

How models are distributed to appliances and how to manage release channels across your fleet.

Coming soon

Node Licensing

How per-appliance node counts work, what counts as a node, and how to upgrade capacity as demand grows.

Coming soon

Operations

Running ZenAI in production

Day-two guides for the teams that keep ZenAI appliances tuned, healthy, and compliant inside their own environment.

Inference Tuning

Throughput, latency, and resource configuration for production inference workloads on a ZenAI appliance.

Coming soon

Troubleshooting

Common provisioning, license, and inference failures, each with clear diagnostic steps to get appliances serving again.

Coming soon

Security & Compliance

API key handling, model integrity verification, and audit access for environments with strict governance requirements.

Coming soon

Need a hand

Can’t find what you’re looking for?

Detailed ZenAI guides are on the way. In the meantime, review the ZenAI product overview or reach the Zentryc team to plan an on-premises deployment.