Veto Protocol — security for autonomous AI agents

veto
systems operational
VETO.EXEPRODUCT / 001

root/security/agent-control

Your AI agents
need boundaries.

Veto is a programmable security layer that controls what AI agents can do across your apps, data, and wallets.

Start building ↗How it works ↓
request→policy→allowapproveblock
THE PROBLEMWHY NOW

AI permissions were designed for people—not autonomous agents.

OAuth can connect a tool. It cannot decide whether an agent should read a confidential file at midnight, share customer data, or execute a high-value trade while you are away.

Authentication proves identity.
Veto controls behavior.
CAPABILITIESPOLICY ENGINE
01

Continuous authorization

Evaluate permissions when an action happens—not only when an account connects.

02

Presence-aware protection

Apply different rules when the user is active, away, offline, or locked.

03

Human approval

Pause sensitive files, transfers, and destructive actions for passkey confirmation.

04

Emergency lock

Suspend every agent session and connected service from one control.

HOW IT WORKSONE DECISION BEFORE EVERY ACTION
01

Connect

Link an app, wallet, data source, or agent.

02

Define

Describe what is allowed, limited, or forbidden.

03

Evaluate

Send the intended action to Veto before execution.

04

Decide

Allow, block, or request human approval.

05

Record

Write the complete decision to an audit trail.

USE CASESEVERYWHERE AGENTS ACT
apps/

Applications & data

Control agent access to Gmail, Drive, Slack, GitHub, databases, and internal tools.

open ↗
onchain/

Onchain finance

Enforce trade values, approved assets, protocols, slippage, schedules, and daily limits.

open ↗
enterprise/

Enterprise agents

Centralize policies, delegated administration, approvals, and compliance records.

open ↗
devtools/

Developer tools

Restrict repositories, environments, commands, credentials, and deployments.

open ↗
ROBINHOOD CHAINONCHAIN CONTROL

policy-controlled finance

Agents can move quickly without receiving unlimited control.

Set maximum trade value, approved tokens and protocols, daily loss limits, slippage, schedules, geographic rules, and human approval thresholds.

policy treasury-agent

trade_limit $500

slippage_max 1.0%

presence away

result APPROVAL_REQUIRED

DEVELOPERSONE API CALL

developer/quickstart

Ask Veto before
your agent acts.

A simple decision API sits between your agent and its tools. Connect any model, application, or smart account.

Read the Docs
const decision = await veto.evaluate({\n  agent: "treasury-agent",\n  action: "wallet.swap",\n  value: 850,\n  presence: "away"\n});\n\n// → approval_required
SECURITYDENY BY DEFAULT
0unrestricted
credentials
  • Short-lived, scoped credentials
  • Passkey-protected approvals
  • Signed webhook events
  • Immediate session revocation
  • Immutable decision logs
  • Policy simulation before launch

ready/status

Let agents work.
Keep your veto.

Continuous consent, programmable policies, and human control for the agentic economy.