Skip to content
Security & trust

Autonomy you can trust

We give AI employees real access to your systems — so the controls that govern what they can do, who approves it, and how it is recorded are the product, not a footnote. This page sets out the posture we run today. We describe only what we have built.

Security questions? security@usermode.ai

The controls

The posture we run today

Grouped by where the risk lives — where the work runs, what an agent is allowed to do, what data we hold, and how it is all evidenced.

Hosting & isolation

Your fleet runs in your own cloud

Each customer is deployed into a dedicated Microsoft Azure environment. There is no shared runtime between clients.

Per-tenant Azure isolation

Every deployment gets its own Azure subscription, resource group, Key Vault and container environment. Tenants do not share compute, storage or secrets.

Default-deny ingress

Services are closed to the public internet by default. Inbound access is permitted only through explicit allowlists scoped to the systems that need it.

OAuth 2.1 gateway

Access to the agent gateway is authenticated with OAuth 2.1 through Microsoft Entra ID — PKCE and signed JWTs, brokered by your own identity provider.

Agent governance

What an agent can do is enforced, not requested

Autonomy is bounded by code. An agent cannot take an action it has not been granted, and sensitive actions stop for a person.

Fail-closed tool policy

A three-layer tool-policy engine evaluates every action before it runs and denies by default. Read-only roles are technically prevented from changing your systems — not just told not to.

Signed outbound grants

Every external send requires an HMAC-SHA256 authorisation that is time-limited and bound to the specific recipient. An expired or mismatched grant is refused at dispatch.

Human approval gates

Spend and sensitive actions pause for a named person before anything leaves the building. The agent acts the moment it has the go-ahead, and not before.

Data handling

We hold as little of your data as the work allows

Operator logs are written to be safe to read. Untrusted inbound content is treated as hostile by default.

Redacted logs

Agent memory content, queries and personal data are not written to operator logs. Diagnostics are designed to be safe to read without exposing what an agent saw or stored.

We never train on your data

Your operational data is used to do your work — nothing else. We do not train models on your data, and we do not pool it across tenants.

Prompt-injection sandboxing

Untrusted inbound content — emails, documents, web pages — is sandboxed so instructions hidden inside it cannot escalate an agent's permissions or trigger actions on their own.

Assurance

Every action is recorded and every change is checked

What an agent did is attributable and durable. What we ship is scanned for secrets, vulnerabilities and broken guardrails before it reaches you.

Tamper-evident audit ledger

Every action is attributed and written to an append-only, tamper-evident security-event ledger with 90-day retention. The record cannot be quietly rewritten.

Secrets and code scanning in CI

Gitleaks and CodeQL run in our continuous-integration pipeline, blocking leaked credentials and known vulnerability classes before a change is merged.

Automated guardrail tests

End-to-end contract tests exercise the safety guardrails on every change, so a regression that would weaken a control fails the build rather than reaching production.

Compliance roadmap

Honest about what we hold today

We will not claim a certification we have not earned. Here is exactly where we stand: the certified infrastructure we build on, and the assurances we are working towards.

Inherited from Microsoft Azure

Inherited

Usermode runs entirely on Microsoft Azure, whose data-centre infrastructure is independently certified. These are the platform’s certifications, which our hosting inherits — they are not certifications of Usermode itself.

  • ISO/IEC 27001
  • ISO/IEC 27017
  • ISO/IEC 27018
  • SOC 1, 2 & 3

Microsoft publishes the current scope of these certifications in the Azure compliance documentation.

On our roadmap

Pursuing

We are building towards our own formal attestation. A SOC 2 examination is on our roadmap. Until we hold it, we will not imply that we do.

If you are evaluating Usermode against a specific control framework, we are happy to walk your security team through our architecture, data flows and the controls described above.

Security & trust

Talk to our team about security

Bring your security questionnaire, your control framework, or your hardest 'what if'. We'll walk your team through the architecture, the data flows and the controls — in detail.