Active pilot · Regulated financial institutions

Authorization
Network for
AI Agents.

AIIAN connects high-risk AI agent actions to enterprise approval, risk, and audit processes — before they reach real systems.

Without enterprise approval, the action does not proceed.

Request Invitation Try the demo
POST /aiian/evaluate
Request
{
  "action_type": "payment.execute",
  "agent_id":    "agent-sg-01",
  "payload": {
    "amount":       2800000,
    "currency":     "GBP",
    "counterparty": "XY Corp"
  }
}
Response · 141ms WOULD_RELEASE 
{
  "decision":     "WOULD_RELEASE",
  "pao_id":       "pao_a3f7c291",
  "expires_in":   300,
  "payload_hash": "sha256:7f3ab2…",
  "evidence_id":  "evd_88c4f1"
}

Live response · AIIAN Cloud Sandbox

Works with your stack

Claude Code LangChain AutoGen MCP Server REST API Azure AI Foundry
DORA MiFID II Basel III J-SOX FCA

The chain-of-command problem

AI agents don't just
recommend. They execute.

A Singapore clearing agent receives an instruction from a Tokyo orchestrator. It can verify the instruction came from another agent. It cannot verify that a human authorised it, that the amount is within limits, or that the counterparty passed sanctions screening — unless something upstream enforced those checks and left proof.

Four failure modes. All silent. All undetectable at the execution boundary.

Identity spoofing — agent claims authority it was never granted
Payload tampering — instruction modified between agents
Replay — valid instruction re-executed against a new position
Race — two concurrent agents exceed a shared limit

Tokyo · Orchestrator Agent

"Execute settlement · ¥420,000,000 · Counterparty XY"

Singapore · Execution Agent

Identity verified. But: sanctions? Limits? Human approval?

No way to know. No proof exists.

External Settlement System

Executed. Irreversible. £2,800,000 moved.

How it works

Enterprise-controlled
before executed.

Enterprise approval at the decision point — not inside the agent prompt, not reconstructed after the fact.

1

Propose

Before executing a high-consequence action, the agent calls AIIAN with the full action payload.

POST /aiian/evaluate
→ action_type, payload, agent_id

2

Evaluate

AIIAN evaluates the request against enterprise policy. Approved or blocked — with a complete record either way.

identity_verifiedPASS
amount_within_authorityPASS
sanctions_clearPASS
human_approvedPASS
3

Execute

The action is approved or blocked according to enterprise policy. The outcome is recorded immediately — ready for audit.

pao_a3f7c291 · approved
single-use · audit recorded

Policy is controlled by the enterprise — not embedded in the agent. Every decision is recorded.

What AIIAN provides

The full execution
control stack.

One governance layer above all agent frameworks. Enterprise approval, risk controls, and audit — regardless of what stack your agents run on.

Authorisation Proof

A verifiable, single-use authorisation token tied to the specific action and approval context. Prevents misuse and replay across different actions.

Policy Engine

AI agents request approval before acting. AIIAN evaluates each request against enterprise policy and approves or blocks it. Policy stays with the enterprise — not inside the agent.

Audit Trail

Every approve and block decision is recorded at the moment of evaluation. Ready for regulatory review, underwriter verification, or internal audit.

Consistent Risk Controls

AIIAN helps enterprises apply consistent risk controls across multiple agents. When limits are reached, controls apply uniformly — not just on the next reporting cycle.

Role-Based Controls

AIIAN helps enterprises manage role-based controls across multi-agent workflows, ensuring agents act within their intended authority at every step.

Human Review

Above-threshold actions are held for human review before proceeding. Reviewers approve or reject via a secure interface. Every review decision is recorded.

AIIAN Cloud Sandbox

Test the authorization
layer before
you deploy.

Shadow-mode execution control. Run realistic payment scenarios against two pre-configured demo ControlPacks — no production system connections required.

  • Evaluate actions — WOULD_RELEASE / WOULD_INHIBIT / NEEDS_APPROVAL
  • Issue and verify sandbox authorisations
  • Execute mock payments against the authorisation lifecycle
  • Retrieve evidence records for audit
Get sandbox key
AIIAN Cloud Sandbox 
# Evaluate a payment action
curl -X POST \
  https://aiian-gate-node.../sandbox/actions/evaluate \
  -H "X-Sandbox-Key: sbx_..." \
  -H "Content-Type: application/json" \
  -d '{
    "tenant_id":   "demo_bank",
    "agent_id":    "my-agent-01",
    "action_type": "payment_instruction.create",
    "payload": {
      "amount":          450000,
      "counterparty_id": "cp_acme",
      "sanctions_status":"clear"
    }
  }'

# Response
{
  "decision":          "WOULD_RELEASE",
  "evidence_record_id":"evd_3a9f12",
  "payload_hash":      "sha256:b4c2f…",
  "severity":          "none"
}

Regulatory compliance

Built for regulated
environments.

DORA Art.28

ICT risk management for EU financial entities

MiFID II

Algorithmic trading controls & audit trails

Basel III

Operational risk & internal controls framework

J-SOX · FCA

Japan & UK financial services governance requirements

Compliance information attached to every decision event automatically. Internal control evidence for AI-initiated transactions — ready for audit.

Get started

If your agents act,
AIIAN controls
the gate.

Active pilot with regulated financial institutions. Settlement, FX, procurement, contract commitments — if your agents execute high-consequence transactions, we want to talk.

Pilot access is by invitation. We respond to every request personally. No sales funnel.

Email hello@aiian.ai Try the live demo

Initial focus: financial institutions operating under DORA, Basel III, MiFID II, and J-SOX.