AI can propose. It cannot execute.

Stop unauthorized AI payments before they happen.

  • Keep AI moving at machine speed.
  • Authorize with human intent.
  • Prove every decision forever.

AI operates at machine speed. Yebo verifies that every payment is backed by an authorized cryptographic mandate before execution, without slowing your automation.

Every decision produces independent proof an auditor can verify years later, even without access to Yebo.

Policy Eval

<50ms

Policy evaluation time is server-measured and returned on every decision response (X-Yebo-Eval-Ms).

Posture

Fail-closed

If approval or verification cannot be confirmed, the transaction will not execute.

Audit

Immutable

Cryptographically signed mandates and receipts are tamper-proof and verifiable years later, even offline.

Built for Finance, SecOps, Risk, and Audit teams who require absolute control and independent proof for AI-initiated payments.

Who This Is For

01

AI Already Prepares Payments

Your AP platform or AI agents prepare or initiate vendor payments as part of normal operations.

02

Unauthorized Payments Aren’t an Option

A single unauthorized payment could create financial loss, regulatory exposure, or reputational damage.

03

You Need Independent Proof

Your CFO, CISO, or auditor expects verifiable proof that the right person authorized every payment before funds moved.

If all three are true, you can pilot Yebo in 14 days using a single payment workflow.

The problem

Disbursement controls built for humanscannot evidence machine-originated payments.

Software now proposes and initiates payments. The controls that evidence approval of those payments were designed for human-speed workflows, and the evidence they produce lives in systems you do not control.

01

Payments are becoming machine-originated

AP automation already proposes vendor payments; increasingly it initiates them. Finance is moving toward machine-originated execution, and the shift is happening while your control narratives are being written.

02

Controls were calibrated for human-speed workflows

Approval workflows, role grants, and review queues assume a person at every step. They are not broken; they are miscalibrated. They evidence that a workflow ran, not that a human approved a specific payment.

03

Approval evidence dies with the vendor

Today the approval lives in an AP platform's logs, an email, or a Slack thread. Three years later, when your auditor tests that control, the vendor relationship may be gone and the logs with it. A rail cannot certify itself.

04

Executives certify it anyway

Under Sections 302 and 906, your officers personally certify controls over every disbursement, including any that software initiates. They need a durable artifact behind that signature, not a log to read after.

How Yebo works

Intent, verified before execution.

A three-stage pipeline sits between every agent and every sensitive action. Each stage is deterministic, recorded, and impossible to bypass.

STEP 01

Intent

The agent declares what it wants to do, in structured form. Action type, parameters, target, caller identity. Every call is a signed proposal, not a side effect.

{
  action: "transfer.funds",
  amount: 4_200_00,
  destination: "acct_8a4f"
}
STEP 02

Policy verification

Yebo evaluates the intent against your policy bundle in milliseconds. Deterministic rules, scoped permissions, threshold checks, and dependency graphs, all enforced before the runtime sees a single side effect.

policy: payments.transfer
match: amount < 5_000_00
       && destination ∈ vendors
=> ALLOW
STEP 03

Authorized execution

Only verified actions reach your runtime. Each one carries a signed mandate (a Yebo Authorization Certificate) that proves what was approved, by which policy, against which agent identity. Replayable, auditable, and tamper-evident.

decision: ALLOW
mandate:  yac_a1b2c3d4
policy:   payments.below_threshold
verified: 2026-05-15T17:24:08Z

Runtime enforcement

Policy is not a guideline.It is a gate.

Yebo is the enforcement layer between agent intent and runtime execution. Every property below is checked at call time, on every action, with no exceptions and no overrides.

  • 01

    Deterministic verification

    Every decision is the output of a pure policy function. Same input, same outcome, every time. No model, no stochasticity, no drift.

  • 02

    Runtime policy checks

    Policies execute inline at the call site, not at deploy time. Updates propagate instantly across every agent, every fleet, every region.

  • 03

    Immutable audit trails

    Each verification produces a signed mandate. Replay any decision months later with the exact policy, parameters, and identity that produced it.

  • 04

    Scoped permissions

    Agents receive narrow, time-bound capabilities, never a blanket key. Scope is enforced at the gate, not assumed by the caller.

  • 05

    Fail-closed by default

    If policy is unreachable, ambiguous, or mid-update, the action does not execute. Silence is denial. There are no implicit allow paths.

Live proof flow

Every action moves through the gate.One stage at a time.

A payment executes only after every stage of the mandate pipeline passes. Watch a single request traverse the runtime.

Execution Integrity Monitor
Concept demo
  1. Active

    01

    Request enters

    Agent action received with scoped execution context.

  2. Pending

    02

    Policy engine validates

    Runtime policy checks permissions, limits, and risk rules.

  3. Pending

    03

    Human intent verified

    Approval boundary confirms the action matches authorized intent.

  4. Pending

    04

    Execution fingerprint generated

    Idempotency key and execution hash are created before commit.

  5. Pending

    05

    Side effect committed

    Approved action executes once, with audit proof stored.

Verified execution complete
01 / 05

Deterministic, policy-bound, and fail-closed. AI can propose. It cannot execute.

Use cases

One wedge, done properly:AI-initiated vendor disbursements.

Yebo sits in front of vendor disbursements over threshold and requires proof of human approval before the payment rail ever sees the call.

Vendor disbursements

Bound vendor payments and payouts to verified policy. Threshold-gated, vendor-scoped, replay-resistant. This is the workflow the 14-day pilot validates.

amount ≥ 10,000 USD ⇒ requires.mandate

AP automation

Your AP platform or AI agents keep proposing payments exactly as they do today. Yebo sits in front of the disbursement and requires the signed mandate before execution.

agent.propose ∧ human.sign ⇒ execute

Approval evidence

Every over-threshold disbursement produces a signed artifact your auditor can re-verify independently - sampled, obtained, and tested like any approval control.

verify(artifact, public_key) = PASS

Developer experience

An SDK call, a policy file,and a signed mandate.

Drop Yebo in front of any sensitive call. Policies are versioned text. Execution runs through the gateway and returns a deterministic decision and a tamper-evident mandate. Nothing else changes about your runtime.

01 · API

Execute through the gateway

typescript
import { Yebo } from "@yebo/sdk";
const yebo = new Yebo({ apiKey: process.env.YEBO_KEY });

// The agent never holds rail credentials.
// Execution goes THROUGH the gateway - no mandate, no movement.
const result = await yebo.execute({
  agent:  "ops-runner-3",
  action: "transfer.funds",
  params: { amount: 18_500_00, currency: "USD", destination: "acct_8a4f9c" }
});
// result.status: "executed" | "pending_approval" | "denied"
// result.mandate: signed YAC - the audit artifact
The caller can't skip the check, because the caller can't reach the rail.

02 · Policy

Schema as code

policy
policy "payments.transfer" {
  match action == "transfer.funds"

  allow {
    amount      < 5_000_00
    currency    in ["USD", "EUR"]
    destination in vendors.approved
    agent.scope contains "payments:write"
  }

  require {
    mandate
    audit.signed
  }
}

03 · Mandate

Signed mandate (YAC)

json
{
  "decision": "ALLOW",
  "policy":   "payments.transfer",
  "agent":    "ops-runner-3",
  "params":   { "amount": 420000, "currency": "USD" },
  "mandate":  "yac_a1b2c3d4e5f6",
  "verified": "2026-05-15T17:24:08.412Z",
  "signature": "ed25519:b9e3...4f2a"
}

Security & auditability

Cryptographic proof of every decision.For your auditors, your regulators, and you.

Compliance is not a layer on top. It is a property of the gate itself. Every action that touches Yebo leaves behind a verifiable artifact.

01

Immutable audit history

Every verification, allowed or denied, is appended to a tamper-evident log. Reconstruct any decision, byte for byte, years later.

log.append(mandate) → root: 0x9c4e…b1f0
02

Verification before execution

Policy evaluates the full action graph before a single side effect runs. Denials block in microseconds; allowances carry a signed proof forward.

verify(intent) → ALLOW · 38ms
03

Execution traceability

Every mandate links agent identity, policy version, parameters, and downstream call. Investigations end with a single ID, not a forensics project.

yac_a1b2c3 → agent · policy · txn
04

Policy enforcement layer

Policies are versioned, signed, and applied at runtime. There is one source of truth, one place to change, one place to audit.

policy@v42 · signed · enforced
Hardware-bound keys
Fail-closed posture
Vendor-independent proof
Auditor re-verifiable

Independent verification

Don't take our word for it

Download a real signed mandate and re-verify it yourself - offline, with an open-source verifier, no account, and no access to our systems. Then tamper with it and watch verification fail.

Infrastructure for autonomous finance

Make every payment carryproof of human approval.

Deploy Yebo in front of one disbursement workflow today. By the end of the quarter, every payment over threshold ships with a signed, independently verifiable proof of approval.

Request AccessView Architecture

Sandbox access same-day · Pilot proposal within 48 hours