ProductBenchmarkDocsTrustCompanyTalk to us
Kerneva Docs

Documentation

Kerneva sits between your AI agents and your financial systems, evaluating every proposed action before it executes — ALLOW, REVIEW, or BLOCK. Start in Observation Mode, calibrate, then enforce.

The path

01

Get a decision

SDK or REST — your first guarded action in under ten minutes.

Quickstart →
02

Integrate

How evaluation works, request shapes, failure modes, and the SDK.

Integration guide →
03

Operate

Investigations, outcome recording, calibration, and audit.

Operator workflow →
04

Deploy

Hosted, self-hosted, or in your VPC — and the enforcement rollout.

Deployment →

Browse by topic

K

Running an agent that issues refunds,
payouts or credits?

Twenty minutes on how it behaves today, and whether the patterns in the benchmark show up in your own history. No integration needed for the first conversation.

Book 20 minutesTry it yourself

Or write directly: [email protected]