Skip to content

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

SRI
ServicesHow it worksDeploymentSecurityAboutFundingContact
Book a discovery call

How it works

From first call to production in about four weeks.

A fixed, boring sequence, an architecture with no black boxes in it, and hardware sized on your real volumes rather than a spec sheet.

How it works

From first call to production in about four weeks.

A fixed, boring sequence. You always know what happens next and what your security team needs to look at.

  1. 0145 min

    Discovery call

    We look at the work your team actually does and which parts are blocked today. If local AI is the wrong answer for you, we say so on this call.

  2. 02Week 1

    Architecture and sizing

    Model selection, hardware sizing, integration points, and a written data-flow diagram your security team can review and sign off.

  3. 03Weeks 2 to 3

    Pilot deployment

    We deploy on your hardware or a dedicated machine, wire it to a real document set, and put it in front of a small group of real users.

  4. 04Week 4

    Rollout and handover

    Access control, audit logging, monitoring, runbooks, and training. Your IT team can operate it. We stay on for support if you want us to.

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.

Sizing

What the machine looks like.

Three shapes cover almost every deployment. We pick between them during the assessment, on your real volumes rather than on a spec sheet.

Team

01

One department, tens of users

Apple silicon workstation or a single mid-range GPU

  • Document search and internal Q&A
  • Drafting and summarising
  • Quiet office, no data centre needed

Department

02

Several teams, hundreds of users

Single professional GPU in a rack server

  • Larger models at production latency
  • Concurrent use across teams
  • Room to grow without a rebuild

Enterprise

03

Company-wide, thousands of users

Multi-GPU server, or several in a pool

  • Frontier-class open models
  • High concurrency with headroom
  • Failover across nodes

Buy it, or rent the same shape from us in an EU data centre. The software is identical either way.

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.

Book a discovery callEmail us directlySend the security brief instead

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