Months ago I listed what a system needs before an agent can run unattended and treated the list as finished. It wasn’t. A stop button handles the runaway. It does nothing for the run that dies on step nine of fourteen.
The moment you harvest a platform out of an app, the app stops being something you can change quietly. That standing cost lands hardest on the team that built it, and most extraction plans never budget for it.
I argued the way to find a platform’s real boundary was to watch the second team that wanted in. The catch I keep running into: two consumers tell you what they have in common, and that’s not the same thing as what the platform is.
Someone asked how many samples we have and three systems gave three different numbers. The dependency order behind vocabulary, ontology, semantic layers, catalogs, and contracts, and why the piece everything stands on is a role most orgs never seat: the data steward.
Birgitta Böckeler’s harness-engineering framework treats iteration as human work. Someone watches, notices, edits the rules. That assumption breaks the moment agents run overnight. The next move is sensors with memory.
Enterprise data strategy has moved its destination from ‘break the silos’ to ‘vectorize everything.’ The step in between is the layer that makes vectors actually work, and it’s the one most roadmaps quietly skip.
The model is not the system. The system is everything required to make model output selectable, constrainable, auditable, and stoppable. I spent a month building that system. Here’s what it actually looks like.
You built an app. It worked. Then a second team showed up and couldn’t use it without inheriting every opinion you baked in. Congratulations, there’s a platform hiding inside your application.
Code generation is a commodity. The defensible value is knowing whether the output is safe to ship, and almost nobody is building for that.