Skip to content
KLA Control Plane
KLA
Platform / KLA Policy Engine

Put your operating procedures to work as agent controls.

Define what an agent may do, what it must check and when a person decides. KLA applies those rules at the point of action.

Book a demoRead the decision contract

Try a payment rule

Move the threshold or switch the amount. The outcome updates as you go.

Policy Builder
Payment limitsVersion 3

Payment approval rule

  1. When

    An agent submits a payment

  2. If

    Amount exceeds €250,000

  3. Then

    Require approval from Treasury reviewer

Try a sample request

€0€500,000

Policy outcomeRequire approval

The amount exceeds the delegated limit. Hold the submission for treasury review.

Sample request · amount only

A €90,000 payment sits inside the €250,000 limit. Two earlier payments to the same beneficiary today bring the total to €270,000. KLA holds the payment for treasury review.

Whenan agent submits a payment

Ifpayments to the same beneficiary in the last 24 hours, plus this one, exceed €250,000

Thenrequire approval from Treasury reviewer

BeneficiaryHalden Logistics GmbH
  1. Sent€120,000
  2. Sent€60,000
  3. Proposed€90,000

Total in 24 hours€270,000

Require approvalPayment held for Treasury reviewer

Write each step of the procedure as a rule.

Rules compare records, judge what a document or name means, and set what an agent may do on its own. Every rule ends in one of four outcomes.

  • Compare sources

    Whenan agent releases a payment

    Ifthe beneficiary on the instruction differs from the approved account record

    Require approvalPayments operations

  • Judge meaning

    Whenan agent opens a customer account

    Ifthe legal name reads like a placeholder, such as “Test Company Ltd”

    BlockAccount not opened

  • Watch volume

    Whenan agent exports customer records

    Ifthe export holds more than 1,000 records

    WarnExport runs, flag recorded

  • Keep routine work moving

    Whenan agent issues a refund

    Ifthe amount is under €500 and the order shows as delivered

    AllowRefund issued

Keep the version that made the decision.

Each decision keeps the context and the policy version that produced it, so a reviewer can explain it months later.

Action context

What it contains

Agent, tool, requested action and supplied business attributes

Question it answers

What the policy evaluated

Policy decision

What it contains

Policy identifier, version, outcome and reason codes

Question it answers

Why the action proceeded, paused or stopped

Linked outcome

What it contains

Decision Request, review outcome and captured tool response

Question it answers

What happened after the decision

Schemas and examples.

Use the schemas and worked examples to review the integration and evidence requirements.

See how an approval is resolved

Start with a rule your team already uses.

Bring a payment limit, a restricted destination or a tool permission. We write it as a rule and test it on requests that should pass, pause and stop.

Book a demo

A 30 minute working session to scope one workflow.

Policy as Code for AI Agents | KLA