Security

Your field data stays yours.

Yield maps, probe data and field boundaries shape contracts, credit and land value. This is how Canopiq is designed to protect them, and what is in place today versus on the roadmap.

On-device analysisThe core vision engine runs in the browser. Captures don't have to leave the farm office to be analysed.

Keys stay server-sideWhen a cloud model is enabled, its API key is read only by the server and never sent to the browser.

EncryptionTLS in transit; encrypted storage at rest on hosted plans.

Tenant isolationEach organisation's data is isolated in the database, never co-mingled.

Role-based accessOwner, agronomist, crew and viewer roles, set per farm.

SSO / SAMLPortfolio and Enterprise plans, with enforced MFA.

Audit trailUploads, reviews, priority changes and exports are logged.

Data residencyAfrica, EU or Americas regions; private deployment on Enterprise.

Details

Security questions.

Is our imagery used to train models?

No. Your imagery, probe data and yields are never used to train shared models without written opt-in. Enterprise model tuning uses only your own data, in your own tenant.

What leaves our network when we use the on-device engine?

Nothing about the capture. Analysis runs in the browser tab. Only the findings you choose to save are stored.

What does the MVP store today?

The live demo keeps its workspace in your browser's local storage, and demo requests are stored on the server that hosts the site. Hosted multi-tenant storage, SSO and audit logging are part of the pilot rollout.

Can we run Canopiq on-premises?

Yes, on Enterprise. The application is a Node service plus static front end with no dependency on a specific cloud, so it can run on a farm or scheme server.

Need a security review before a pilot?

Talk to us