ON-PREMISES · RUNTIME GOVERNANCE FOR ENTERPRISE AI

An agent tried to wire $50,000 nobody approved.

It got as far as the policy. APERION sits in the path between your agents and every model and tool. It reads the call, stops the action that exceeds the agent's authority, and hands the examiner a record bound to the human who owns it. Inside your environment, across every model you run.

REQUEST A DEMO

SEE THE TRUST FABRIC

What Smartflow did

Fifteen seconds, behind the scenes.

One MCP call. Four things happened before the money could move.

01

Checks the agent's behavior.

Every argument in the call, against policy, before anything executes.
02

Escalates to the human in the loop.

The named person whose authority the agent is using — not a queue.
03

Proceeds only after verification.

A live face check, at the assurance the risk calls for.
04

Records the whole thing.

Examiner-ready hash-chained entry.

Autonomous agents in the wild

Can you name the human behind every model call your agents made yesterday?

Most enterprises cannot, and they find out while looking at a spend report. To attribute a call to a business unit, something has to sit in the path and read it. Once it does, the harder question becomes answerable too: which verified human was this agent acting for, what did it send, and what came back.

Your identity stack was built for people. Agents are not people.

question from
one person

→

unattended
model calls

Thirty-nine of those forty happen with nobody watching.

Chat scales with headcount. Agents scale with tasks, and every task fans out into retrieval, reasoning, tool calls and retries.

Same wire.
Both problems.

One control point

Security

Enforces policy on each prompt, response, and MCP tool call: block, redact, warn, allow, or hold the action for a verified human.

Finance

Meters, routes, caches, and holds the keys.

Both run at the same control point, because both need to see the same traffic. One deployment, on-premises, across any provider.

PROOF IN PRODUCTION

Watch the Trust Fabric work, layer by layer.

THE TRUST FABRIC

APERION ownscompose

L4APERION

Audit & Evidence

“Can we prove what happened to a regulator?”

L3APERION

Runtime Governance

“What is this agent authorized to do, and who decides when it exceeds that?”

L2COMPOSE

Access Governance

Okta · Entra · Active Directory · Veza · SGNL

“What is the human allowed to do?”

L1APERION

Verified-human root

NIST IAL2/AAL2 · your proofing provider, enforced by Smartflow

“Who is the actual human?”

Agent identity

Bound to the verified human

“What identity does the agent carry, and on whose behalf?”

You keep the identity and access you already run, Okta, Entra, AD, Veza.

APERION governs the agent on top of it, from the verified human to the regulator-ready record.

AGENT ACTION

Delete production database

HIGH RISK

Held, awaiting a decision

VERIFIED HUMAN

Cleared by the accountable human

VERIFY

Step-up to the accountable human at the moment of risk.

Every agent acts on a named person's authority. When it reaches past that authority, the action pauses in the path and goes back to that person, through the proofing you already run, at an assurance that scales with the risk: a push to their phone for a routine action, a live face check for a wire. The record shows who decided.

See the Trust Fabric

PROTECT

Shield stops destructive tool calls before they execute.

Shield blocks destructive MCP tool calls before the database, repository, or filesystem receives them.

Explore Shield

APERION Shield terminal demo blocking an AI agent’s database-drop and recursive-delete tool calls.

APERION Compass terminal demo running a local governance assessment and producing a scored evidence report.

PROVE

Compass proves your posture with a local evidence chain.

Compass verifies the evidence chain, scores the current posture, and produces a report locally.

Explore Compass

EXTEND

Extend governance across every connector and workflow.

Govern content connectors, reusable skills, and developer workflows through the same runtime control point.

See Smartflow

Capabilities

What runs in the path.

Compiled Enforcement Path

Rust-based infrastructure. Not a Python library in the request path. Infrastructure-grade performance for production workloads.

Semantic Caching

Four-phase BERT semantic cache. Hit rates depend on the workload, so we measure them on your own traffic during a scoped POC.

On-Premises Deployment

Runs in your data center or private cloud. No cloud dependency. No PyPI supply chain risk. No third-party data exposure.

Identity-Aware Governance

Every AI interaction authenticated against your enterprise IdP over OIDC. Composes with Entra ID, Okta, SAML and Kerberos single sign-on. Per-user audit trails tied to real identities.

Inline Policy Enforcement

No-code compliance engine. Policies enforced before prompts reach any model. EU AI Act, NIST AI RMF, FINRA, HIPAA mapping.

MCP Proxy Governance

Inline governance for agent-to-agent workflows. As agentic AI proliferates, MCP servers are the new attack surface. Smartflow governs them.

Next cohort

Name the human behind every model call.

One workflow, in your environment, on your infrastructure. Our forward-deployed engineers embed with your team and have it in production in under 90 days.