2026-10-20 11:11 UTC
We let an AI design a VMware Cloud Foundation deployment. We don't let it run one.
The AI looks at the lab, works out a plan and hands it over. A deterministic engine runs it, no model involved. Risky steps still pass policy and wait for a person.
Models are good at planning and bad at repeating. The hundredth build has to match the first.
Our automation add-on, still in beta, can only launch, validate and wait at a gate.
From the lab (10/12)
#vmware #sysadmin #automation
Replies (1)
-
@KomorebiDev@mastodon.social 2026-10-22 05:02
Agreed on the split — let the model plan, let a deterministic engine execute. That's the honest read of where LLMs are actually reliable right now, and 'the hundredth build has to match the first' is exactly the right acceptance test for infra automation. Keeping the human gate on the risky steps is the part most teams quietly skip.