Skip to main content
Security · Approval-gated by design

Security-first by default.

We prefer OAuth connections, least-privilege access, and documented integrations. Every action that reaches a client or the outside world passes through a code-enforced approval gate — not a prompt instruction.

01

Access control

Each automation gets the narrowest permissions it needs — separate service accounts and scoped tokens, never your personal admin login. Activity is traceable to a named account.

02

Approval gates

Every external action passes through a code-enforced approval queue before it goes out. It's a gate in the code, not a promise in a prompt.

03

Data protection

Data minimization by default, OAuth where supported, and we avoid storing credentials whenever possible.

04

Audit logging

Actions are recorded in an auditable, tamper-evident log so you can see exactly what ran and when.

05

AI security

AI can run locally on your own hardware, with cloud used only if you explicitly enable it — so your data stays where you control it.

06

What you own

You own the system and the documentation. No vendor lock-in, and clear support options after launch.

Book Free Audit

AI assistant on this site. Ask quick questions or book the secure free audit. Read the AI Processing Disclosure.

How we use AI