#deployment
Every post tagged "deployment".
39 posts · showing 11–20
-
Buying vs Building Agent Capability as a Company
Framed as a technology decision, which is why it goes wrong. One question settles it: if a competitor bought exactly what you're buying, would they have what you have?
-
The Loop Decisions You Only Make Once
Most agent design choices are cheap to revise. Six aren't — and in every case the answer that ages well is the same one, for the same reason.
-
Lock-In Risk in Agent Tooling, and How to Keep Optionality
The API call is trivially portable — the coupling forms in four other places, and the worst one isn't technical at all. One question tells you how exposed you are.
-
The Case for a Local-First Agent Stack
The cost argument for local-first is weak and the ideology one is worse. The case that holds is dependency control — and it comes with a permanent operational tax nobody budgets.
-
What Runs Locally Today and What Still Won't Soon
Local handles the steps; hosted handles the orchestration. The agent loop is the hardest thing to localize, because it stresses all three local constraints at once.
-
Will On-Device Intelligence Be Free? What the Economics Say
"Free" means three different things here. Two are plausible and already partly true; the third doesn't follow, because the frontier is defined by requiring the most compute.
-
The Cost of Choosing Your Model Too Early
The choice is rarely the mistake — the accumulated compensations are. Prompts absorb quirks, the harness papers over weaknesses, and none of it looks like coupling until you try to change something.
-
The Deploy Step Nobody Should Automate Yet
It's the easiest step to automate, saves the least time, and carries the largest tail risk. Automate the readiness report and the rollback instead — and separate deploying from releasing.
-
Upgrading One Agent in a System of Six
A contained improvement to one classifier made the supervisor above it drop half its escalations. No error, no failing test — because each agent's own tests passed against its own version.
-
Agents Get Worse While You're Not Touching Them
Nobody edits anything and six months later it handles a whole class of request worse. Five things decay on their own — and none of them announce themselves by breaking.