Blog
Working notes on architecture, cloud infrastructure and AI systems — written as things ship.
Every AI session normally starts from zero. An animated tour of how myAI gives every model the same memory, tools and to-do list — the 08:00 boot, git-versioned memory, distillation, recall, one gateway, a local runner and a multi-model swarm.
A front desk answered visitors from six different tools on a shared tablet. Seven weeks later it runs on one screen that stores none of their data: every tile reads its source of record, the network decides who signs in, and the design fails closed. The architecture, the day it broke, and what is not proven yet.
A staff-picks feature for a museum visitor app went from pitch to a production prototype the same afternoon, then from CMS schema to TestFlight and the Play internal track in about thirty hours. Prototype the contract, not the screens: one shape, four teams building in parallel, a source label on every response, and a shared release pipeline with no special path.
Two months of changes to myAI since the last architecture post — a universal daily boot, a brain that surfaces prior art and grades its own health, a fleet-wide MCP bridge, self-hosted CI runners, and the doorway that lets me drive the whole thing from my phone.
Assessing a multi-channel visitor platform against four real failure modes instead of a tooling wishlist. Three telemetry dialects, correlation that breaks at every boundary, alerts that fire into a portal, why the join with SaaS vendors has to run on business keys, and the order that matters: an alert that reaches a person, then correlation, then the panel.
A front-of-house dashboard built for a wall-mounted tablet and a flaky venue network: a backend-for-frontend that keeps every credential off the device, the ops team's own tools used without being called, and offline data that knows what to forget. Then the rules underneath every repository: decisions written before code, one path to production, infrastructure enforced by policy, and why a rule that is not checked is only a preference.
A high-traffic visitor platform accumulated five cache layers that each kept their own opinion of time. How one monotonic version stamp made them agree — why freshness is a property of a field, not an endpoint — and how to arrive warm at a checkout you don't control.
One question decides how a governed dashboard is licensed, secured and paid for: when the query reaches Power BI, whose name is on it — the person, or the application?
AgentFlow turns an idea typed into a text box into a repository you can actually run — the architecture that gets from prompt to working project.
A content layer that answers before it's asked — one document as the source of truth, read across every channel the museum owns.
A control-plane seam that turns “which cloud” into a runtime detail — six methods behind one interface, so the platform stops caring where it runs.
Treating the job search as a data pipeline — ingest, assess, shortlist, align — and why the most useful AI hiring tool is the one that gets out of the way.
Building an event backbone around a system that emits no events — the enterprise pub/sub integration pattern behind the museum's content estate.
Governed Power BI embedded inside our own React app — a relay that owns nothing, brokering access without holding state or data.
How we connected Auth0 to Tessitura TNEW ticketing with nothing but a post-login hook and a REST call. As far as I can tell, the first time it has been wired this way in Australia.
The architecture of myAI — a git-versioned memory layer, a specialist agent fleet, an autonomous off-hours runner, and an MCP gateway that ties them together. How it works, why it's shaped this way, and where it could go.
The architecture of Connect — an installable support hub where a bug report becomes an AI-triaged, human-approved, autonomously-built fix with a live public timeline. The triage→fix loop, the safety model, and how a year of plans reshaped the ambition.