Selected projects, in production.

Systems designed, built and operated end to end, all still running: an agent orchestration control plane inside a regulated organisation, a public evaluator for agent skills, and a self-hosted finance tracker.

01

AMOS.

Software · AI infrastructure · Ongoing
ArchitectureChatThreads and mentionsCode hostPull requests and reviewsIssue trackerTickets and commentsControl planeRoutes every request and correlates each surface to one sessionDispatchOwning teamRouteRules first, model lastInvestigateRead-onlyPermission gateIn code, fail-closedActPer requesterSession registryOne session across every surfaceCredential brokerShort-lived, scoped credentialsTelemetryEvery call: cost, latency, outcome

An AI agent orchestration control plane in production across a large regulated organisation: deterministic routing, read-only investigation before any action, and permissions enforced in code.

Role
Architecture, build & operation
Stack
Go · Kubernetes · Postgres · harness-agnostic AI layer
Read the case study
02

Agents Skill Eval.

Software · Web app · 2026
Evaluation runchangelog-formatter01QueuedComplete02AssignedComplete03StartedComplete04DeterministicComplete05AI reviewComplete06FinalizingComplete07CompleteCompleteOverall result96ExcellentSpec compliance100Security96Token budget92Effectiveness95

A production evaluator that scores agent skill packages on spec compliance, security, token cost and effectiveness, with a machine-readable report built for CI.

Role
Design, frontend, evaluation engine
Stack
Deterministic checks, optional AI review
Read the case study
03

WealthTrack.

Software · Self-hosted · 2025
Net worth · household€1.571.282+24.655 this periodYTD6M1Y2Y5YMaxSep 2025TodayProjection · Sep 2027AllocationIndex funds38%Real estate27%Cash15%Retirement12%Crypto8%

A self-hosted household net-worth tracker: one container, plain-text data, crash-safe writes and charts that make a decade of trend readable at a glance.

Role
Full-stack design & build
Stack
Vue · TypeScript · Hono · Docker
Read the case study

Have something that needs building?

Describe the system, who uses it and what it has to survive. You get a written view on scope, architecture and the first increment worth shipping.

Start a conversation