The authority API for AI agents · veracta.net

Control what your AI agents are allowed to do.

Veracta is a lightweight authority API that lets AI agents check whether an action should be allowed, blocked or escalated before execution.

Join early access View API demo

Before your AI acts, ask Veracta.

AI Agent

wants to act

Veracta

authority check

Allow

Escalate

Block

Audit Trail

every decision

The problem

AI agents are moving from advice to action.

AI agents can now send emails, update systems, approve work, access data and trigger workflows. But most businesses do not have a simple way to decide what those agents are allowed to do, when approval is required and who owns the outcome if something goes wrong.

Identity tells you who the agent is.

Access tells you what it can reach.

Veracta tells you what it is allowed to do right now.

The core idea

Human-approved authority, not approval for everything.

Veracta lets organisations define authority boundaries. Low-risk admin can happen automatically and be logged. High-risk actions involving money, reputation, sensitive data or external commitments can escalate for approval. Actions outside authority can be blocked.

How it works

One API call between intent and action.

Agent requests action

An AI agent prepares to send, spend, approve, access or trigger something in the real world.

Veracta checks live decision state

Veracta evaluates the relevant context around the specific action being attempted.

Veracta returns allow, escalate or block

A single, proportional decision is returned before the action executes.

Every action is recorded

Each decision creates an immutable audit trail with the reason and policy matched.

Decision state

Authority depends on context.

Veracta does not need to understand the whole live state of a business. It captures the relevant decision state around the specific action an AI agent wants to take.

Action typeTransaction valueRisk levelReversibilityConfidenceEvidence qualityExternal commitmentData sensitivityRecipient or supplier statusDomain permit listDomain deny listHuman ownerExisting policy

Authority doctrine

State-dependent, proportional, revocable and auditable.

Authority should not be a permanent label. It should expand or contract based on the action, context, risk and evidence available at the moment an AI agent tries to act.

Low-risk, reversible, low-value actions→Allow and log

Medium-risk or uncertain actions→Escalate for approval

High-risk, blocked or unauthorised actions→Block

Everything Audit trail

API demo

Add authority checks to your AI agent in one API call.

Request

POST /v1/check-authority

{
  "agent_id": "finance_agent_01",
  "organisation_slug": "veracta-demo",
  "action_type": "approve_invoice",
  "action_summary": "Approve invoice from ABC Supplies for £1,250",
  "value": 1250,
  "currency": "GBP",
  "risk_level": "medium",
  "confidence": 0.82,
  "reversibility": "medium",
  "external_commitment": true,
  "data_sensitivity": "low",
  "recipient_domain": "abc-supplies.co.uk",
  "domain_status": "approved",
  "human_owner": "mike@gamesterinc.com"
}

ResponseESCALATE

{
  "decision": "ESCALATE",
  "reason": "This action involves money, creates an external commitment and exceeds the approved automatic authority limit.",
  "next_step": "request_human_approval",
  "audit_id": "audit_123",
  "authority_status": "outside_automatic_authority"
}

Use cases

Wherever AI agents take real actions.

AI finance agents

AI sales agents

AI support agents

AI admin agents

AI workflow automation

AI agents inside Slack, Teams, CRM and finance tools

Differentiation

Not another chatbot. Not another compliance dashboard.

Veracta is an action authority layer. It does not replace IAM, security or governance platforms. It gives builders a simple API to check authority at the moment an AI agent tries to act.

IAM

Controls identity and access.

AI governance

Manages policies, compliance and evidence.

Veracta

Controls action authority before execution.

Who uses Veracta

Builders integrate. Businesses control.

Agent builders integrate Veracta, but businesses control the authority boundaries. Every escalation routes to a named human owner.

Agent Developer

The developer or agency building the AI agent. They integrate the Veracta API into their agent code.

Company / End Customer

The business using the AI agent. They own the authority rules, human approvals, policies and audit trail.

Human Approver

The named person inside the company who approves, rejects or requests changes when an AI action is escalated.

Pricing

Start free. Upgrade when your agents start acting.

Start free. Add authority checks to your agent in minutes. Upgrade when your agents start acting in real workflows.

Free

£0/month

For testing and early builders

Includes 1,000 authority checks/month

Get started

Starter

£29/month

For solo builders and small agents

Includes 10,000 authority checks/month

Get started

Growth

£99/month

For SMEs and active agent workflows

Includes 100,000 authority checks/month

Get started

Agency

£299/month

For agencies managing multiple client workspaces

Multiple client workspaces and higher usage

Get started

Enterprise

Custom

For larger companies needing SSO, compliance support, custom limits, data controls and support

SSO, compliance and data controls

Company-owned account

The company owns the Veracta workspace and pays directly. Developers are invited as integrators.

Developer / agency account

The developer or agency pays for Veracta and includes it in their agent build or monthly support package.

For developers

Developers use Veracta to make their AI agents safer and easier to sell.

For companies

Companies use Veracta to control what AI agents are allowed to do before they act.

Early access

Building AI agents? Add authority before action.

Veracta v0.1 is the first live API. Join early access to add allow / escalate / block authority checks to your agents.

Before your AI acts, ask Veracta.