Skip to content

Two engineers, a small number of deployments at a time. Currently taking on new work.

SRI

Security and governance

Nothing leaves the network. Here is how that is enforced.

Inference happens on your machine. There is no call out to a model provider, so the processor, the transfer, and the retention question all disappear at the architecture level rather than in a policy document.

For your security team

You are probably not the person who has to approve this.

Whoever has to sign it off will want the architecture, the data flow, and the governance answers in one place they can read without you in the room. This page is that document. Print it to PDF and send it on.

Governance

The questions an auditor opens with.

We are not your compliance officer. We build the architecture that makes these answers short.

GDPR

Who processes personal data, and where?

You do, on your own infrastructure. No third-party processor and no international transfer to assess.

EU AI Act

Can you document and control the system you deploy?

Model version, weights, prompts, and retrieval sources are all pinned and versioned in your repository.

Sector rules

Does patient or client data stay in the estate?

It never leaves. Air-gapped deployment removes the network path entirely, not just the policy.

Continuity

What happens if the supplier disappears?

Open weights, open components, documented configuration, and your team holds the runbooks.

Reference architecture

What we actually install.

No black box. Every layer is an open component your team can read, audit, and operate without us.

01

Access

Web UI and an OpenAI-compatible endpoint behind your own SSO

  • OIDC / SAML
  • Reverse proxy
  • Per-team API keys
02

Orchestration

Retrieval, prompt assembly, tool calls, and per-request policy

  • RAG pipeline
  • Role-based scoping
  • Full query audit log
03

Knowledge

Your documents, chunked and embedded, indexed on your own storage

  • Vector store
  • Connectors
  • Incremental sync
04

Inference

Open-weight models served locally, pinned to a version you approve

  • Model server
  • GPU or unified memory
  • Version pinning
05

Operations

Metrics, logs, alerting, and backups wired into what you already run

  • Prometheus / Grafana
  • Log shipping
  • Restore drills

Deployed with Docker and systemd on Linux, or natively on Apple silicon. Configuration lives in your repo, not in our heads.

The decision on one page

Same capability. Different threat model.

This is the table your security officer will build anyway. Here it is up front.

Cloud AI compared with a private deployment by SRI Systems
CriterionCloud AISRI
Where inference runsVendor infrastructure, region of their choosingHardware you own or rent in your own name
Who holds your documentsA third party, under their retention policyYou. The index never leaves your disk
Processor agreement neededYes, plus transfer assessmentNo third-party processor in the request path
Works with no internetNoYes, on-premise and air-gapped
Audit log locationVendor console, exportable at bestYour own log stack, queryable like any other service
Model choiceWhatever the vendor ships and deprecatesOpen weights you pin, upgrade, or roll back
Cost shapePer token, unbounded, scales with successFixed hardware or fixed monthly, flat under load
If the relationship endsAccess stops, data export on their termsThe system keeps running. You already own it

Next step

Tell us what your team is not allowed to do yet.

A 45-minute call. We look at your workflows, your data rules, and whether local AI is worth it for you. If it is not, we will tell you that instead of selling you a project.

Not ready for a call? Send the security brief to whoever has to approve it, or just reply to an email. All three work.