Projects
Most of this work is proprietary, so these describe the problem, the constraints and the reasoning behind the architecture. None of them describe the implementation.
Written to be public-safe. No internal names, customers, source or employer-confidential metrics appear on this site.
A controlled layer between enterprise applications and multiple model providers, so access, routing and policy are decided in one place instead of separately in every application.
Configurable coordination of several specialised agents inside a governed workflow, instead of routing every task through one general-purpose agent.
Platform policies for Model Context Protocol and agent-to-agent communication: how agents find each other, prove who they are, and reach tools safely.
Rate limiting and budget enforcement for LLM traffic across users, agents, organisations, models, providers, tokens and monetary cost.
A gateway capability that lets an organisation immediately cut off a compromised or disallowed user or agent from downstream AI resources.
A scrubbing mechanism for support data that met privacy obligations without giving up the low latency the data was valuable for.
Workflow-automation and review capabilities that let non-specialists build and complete enterprise processes correctly.
Resumable uploads, a faster migration path and a dedicated download service. All three sit where users notice reliability and speed straight away.