Skip to content
KLA Control Plane
KLA

Put AI agents into production. Safely.

KLA checks each agent action against your policy before it runs and sends exceptions to the person who owns them.

Book a demoSee how it works

A 30 minute working session to scope one workflow.

  • Policy before every action
  • Exceptions to their owner
  • Sealed evidence

Programs and memberships

NVIDIA Inception ProgramAssociation Monégasque des Compliance OfficersMonacoTech Startup Program

Standards participation

Member: AFNOR CN IA

Agents run the work.
Your people make the decisions.

KLA checks every agent action against your policy before it runs. Routine work goes through. Exceptions go to the person responsible. Every action is sealed as evidence.

CommandToday · 14:32 · Example data
Actions checked
12,480
Allowed
11,902
Warned
131
Sent for approval
412
Blocked
35
AgentWorkActionsTo reviewStatus
Treasury payments agentSupplier payments3,210188Live
Onboarding agentBusiness onboarding2,94096Live
Claims triage agentMotor claims4,105102Live
Client service agentAccount requests2,22526Live

Decision Desk6 waiting

Compliance officer L2

Pay invoice INV-2048

€420,000

R3 · Payment above €100,000 · One approval

  • Compliance officer L1Pay Ostrava FreightR1 · Payee added in the last 30 days
  • L2, then MLROFund the Arden share purchaseR5 · Payment above €1,000,000 · Two approvals
  • Compliance officer L2Onboard Halden LogisticsR4 · PEP or adverse-media match

Put agents into production with the controls your supervisor expects.

  1. Week 1Scope
  2. Week 2Configure
  3. Week 3Governed traffic
  4. Week 4Production decision

Go to production

Take one agent from pilot to a governed release. The four-week SAFR Production Sprint ends with a verified evidence bundle and a documented production decision.

Scale the work

Agents take the routine volume. Your team reviews the actions your policy sends to them, with the full context on one screen.

Answer the supervisor

Every action, rule, approval, and tool result is on record. Export a Sealed Evidence Bundle when an auditor or supervisor asks.

Figures shown are example data.

Routine actions run on your policy.Exceptions wait for the person who owns them.

Decisions at the point of action

Decide what your agents can do.

Set the operating rule. Exceptions go to the person responsible, and blocked actions never reach the tool.

Decision Desk
Invoice INV-2048

€420,000Supplier payment

Requested by
Treasury payments agent
Operation
Submit payment
Supporting document
Supplier invoice

Approval threshold€250,000

Treasury reviewer

Required approval role

Review payment

The amount triggers the payment-approval rule. The payment stays on hold while treasury reviews the request.

Treasury review required

Policy outcome: require approval

ExecutionPayment submission is heldWaiting for the reviewer’s decision.
Approve or reject the payment in the example.Explore human approval

Govern an existing agent in three steps.

  1. const result = await kla.evaluateToolCall({
  runId: 'inv-2048',
  gateId: 'supplier-payment',
  toolName: 'submit_payment',
  toolArgs: { amount: 420000, currency: 'EUR' },
});

result.decision; // 'require_approval'

    Step 1

    Connect the agent

    Add the KLA Node.js or Python SDK. The agent asks KLA for a decision before each consequential tool call.

    Review integration routes

  2. Whenan agent submits a payment

    Ifthe amount exceeds €250,000

    Thenrequire approval from Treasury reviewer

    Step 2

    Write the rule

    Your team sets limits, permitted destinations, and approvers in Policy Builder, in plain sentences.

    See policy controls
    • AllowThe tool runs.
    • WarnThe tool runs and the warning is recorded.
    • Require approvalThe action waits for its reviewer.
    • BlockThe tool is not called.

    Step 3

    Act on the decision

    Every action gets one of four outcomes. Each outcome, approval, and tool result is recorded as evidence.

    See human oversight

Execution Lineage

Follow what actually happened.

Open the request. Inspect the rule that applied. See who approved it and what the tool returned.

Lineage Explorer connects those events for investigation. Evidence Room collects the material your reviewers need.

Explore execution history
Lineage Explorer
Invoice INV-2048

Payment execution

Submission accepted

  1. Payment requested

    Submit supplier payment · €420,000

    Treasury payments agent

  2. Approval required

    Amount exceeds the €250,000 threshold

    Payment limits · version 3

  3. Treasury approved

    Invoice and approval scope confirmed

    Treasury reviewer

  4. Tool accepted submission

    Submission accepted; settlement not shown

    Payment tool
Request, policy version, human decision, and tool result linked to one example.

Start with the work your team owns.

All use cases
Treasury payments agentSubmit supplier payment€420,000Require approval Treasury reviewer

Payments and treasury

Review transfers above an agent’s delegated limit.

Customer operations agentExport customer recordsExternal analyticsBlock Destination not permitted

Customer data

Restrict exports to the destinations your team permits.

Batch release agentRelease batch recordBR-0417Require approval Quality assurance

Document release

Keep scientific and quality review in the release path.

Claims agentPay claim€1,240Allow Within the approval threshold

Insurance claims

Hold claim payments above an approval threshold for an adjuster.

Common questions

Ask about your own workflow in the first session.

Book a demo
What does KLA do when an agent tries to act?
KLA evaluates the action against your policy before the tool runs. The result is allow, warn, require approval, or block. Actions that need approval wait in the Decision Desk for the person responsible.
What happens while an action waits for approval?
The tool does not run. The reviewer sees the request, the rule that applied, and the supporting context on one screen. Approval releases the action and rejection stops it. Both outcomes are recorded.
Which agents can KLA govern?
Agents you run through KLA Runtime, and agents in your existing stack. Teams add the KLA Node.js or Python SDK, or OpenTelemetry, and KLA checks each consequential tool call before it runs.
Who writes the policies?
Your team defines the allowed operations, destinations, and approval requirements in Policy Builder.
What evidence does KLA keep?
Each action, the rule that applied, the reviewer’s decision, and the tool result. Evidence Room exports a Sealed Evidence Bundle when an auditor or supervisor asks.
Can an auditor check a bundle without access to KLA?
Yes. The export ships with a standalone verifier that checks the bundle with no network access. To confirm the bundle came from KLA, the auditor pins its keys against a key fingerprint KLA publishes.
How long does it take to reach production?
The SAFR Production Sprint runs four weeks on one workflow. It ends with a verified evidence bundle and a documented production decision.
What does the first session cover?
Thirty minutes on one workflow: the agent, the systems it touches, the approval owner, and the evidence you need.

Bring one workflow.
Define the first control.

We’ll review the agent, the systems it touches, the approval owner, and the evidence you need. The evaluation establishes the supported integration route and a clear operating scope.

Book a demo

A 30 minute working session to scope one workflow.

KLA: Move AI from pilot to production with confidence