Security
Trust, built in from day one
We tell you exactly what's live and what's coming. No certifications are claimed during the preview.
Our safeguards
Per-user data isolation
PlannedEvery record is locked to its owner and workspace with database-level rules.
Server-side AI & SMS limits
PlannedHard daily caps and spending budgets checked on the server before any call.
No runaway loops
PlannedOnly a new human message can trigger KAI. KAI never replies to itself or to delivery receipts.
Human approval & Pause KAI
Demo onlySensitive topics always come to you. One tap stops all automation.
AI activity audit log
Demo onlyWho acted, in which mode, when and why.
Encryption
PlannedEncrypted in transit and at rest. KAI is not end-to-end encrypted, because the AI must read allowed messages.
Block & report
Demo onlyStop unwanted contact and flag abuse.