AI platform engineering
Shared platforms for teams building with models: what to standardise, what to expose, and how to tell if it's working.
8 posts, oldest first
- 1 Deciding what not to expose Infrastructure was largely designed for people who read docs and debug by hand; building for agents and for non-infrastructure users both raise the question of what to hide. 14 Sep 2026, 1 min
- 2 Who chooses the model: the application or the platform? Pinning a model version gives reproducibility; letting a platform route by requirements eases upgrades. Model retirement schedules make the trade-off concrete. 24 Sep 2026, 1 min
- 3 First users shape the platform's design A platform's first real users show where its abstractions help and where they get in the way, which makes their feedback part of the design work. 29 Sep 2026, 1 min
- 4 What a shared platform should standardise Shared platforms tend to work best when they standardise the capabilities every team would otherwise rebuild, and leave use-case decisions to the teams. 1 Oct 2026, 1 min
- 5 Gateway errors that help someone fix the problem A blocked request is more useful when the error says what happened, where, and what to try next, without exposing sensitive details. 6 Oct 2026, 2 min
- 6 Measure the journey to the first production call Platform metrics are more useful when they cover how quickly a new team gets started, not only how the platform performs once it's running. 8 Oct 2026, 2 min
- 7 An agent's identity is not its permission Knowing who an agent is answers only part of the question. Whether an action is allowed depends on the user, the scope they delegated and the resource's own policy. 13 Oct 2026, 2 min
- 8 Good abstractions hide complexity, not evidence An abstraction can reduce how much infrastructure a user needs to know without reducing the evidence they need to diagnose a problem. 15 Oct 2026, 2 min