Services

Applied AI

AI that does work, under controls, on hardware you or we control. We run it in production before we recommend it, and we ship the software to prove it.

Server rack in monoline with a closed work loop passing an amber checkpoint

What We Run In Production

Before any of this is offered to a client, it runs our own business.

A Guarded Operations Layer

Our Microsoft 365 administration runs through an AI-assisted layer that plans every change, checks it against live state, refuses anything that would touch a privileged account or escalate a permission, executes, and reads the result back. Refusals are recorded. Rollback is built from a snapshot taken before the write. It has refused unsafe actions during live rollouts and was not overridden.

A Ticket Pipeline at Controlled Autonomy

Every ticket into our service desk receives an AI analysis on arrival. Spam is closed automatically. Duplicate and superseding alerts are reconciled on every sweep. Autonomy is raised one level at a time, with each level proven under real load before the next.

Review Agents on Endpoints

AI review agents on managed workstations audit configuration and report defects, including our own. The first audit found problems in scripts we had shipped. That is the point.

Self-Hosted Models

Our models run on our own GPU hardware. No third-party provider in the loop, no per-query cost, and client data never leaves the environment unless you choose otherwise. Cloud GPUs are used for training runs only, and released when idle.

Software We Have Shipped

Public, reviewed, and in use by people who are not our clients.

StrifeBridge MCP

A WordPress plugin on the official plugin directory that lets ChatGPT, Claude or Gemini manage a site through the Model Context Protocol, with an activity log, safe mode and OAuth. Three independent security audit rounds.

First Resort

An iOS app on the App Store with a fine-tuned model that runs entirely on the device. No account, no network, no data leaves the phone. The model is published openly.

ContextEngine

An npm package that gives AI coding tools persistent context about a codebase. Open source, security-audited.

What We Build for Firms

Automation Under Controls

  • Agentic workflows that take sequential actions, with refusal gates, verification and rollback around each one
  • Inbound request and email triage at controlled autonomy, with a record of what was done and why
  • Document analysis, extraction and summarisation
  • Internal knowledge assistants grounded in your own documents, not the open internet

Private and Edge AI

  • Self-hosted models on your infrastructure or ours, with no data leaving the environment
  • On-device models where the data cannot leave the device at all
  • Real-time inference at the edge with no cloud dependency
  • Data residency and privacy requirements met by design, not by policy

Integration

  • MCP servers that connect ChatGPT, Claude and Gemini to your existing systems, with access you control
  • Operational dashboards and reporting fed from live data
  • AI vision and image analysis integrated into existing workflows

Custom Applications

  • iOS apps in SwiftUI, from design through App Store deployment
  • Web dashboards and backend APIs on self-hosted or cloud infrastructure, your choice
  • The AI layer that connects them, built to production standard rather than as a prototype
  • Ongoing maintenance and feature development

How We Approach It

We do not start from a model. We start from the work: what is repeated, what is slow, what must never happen. The controls are designed first, then the automation is built to run inside them, then autonomy is raised one level at a time as each level proves itself. A system that can refuse is worth more than a system that can do anything.

Tell us what is repeated.

Describe the work your team does the same way every week. We will tell you what can be automated safely, what should stay with a person, and what it would take.