Tagged drift
2 pieces
- · 11 min read
One Core, Many Campaigns: Why Forking the Working Flow Per Tenant Always Drifts
When a product runs many campaigns or tenants, copying the working flow per campaign is the default, and the copies drift. A reliability fix lands in whichever copy somebody was looking at when the bug was reported. Eventually the same inbound event is handled differently depending on which campaign produced it, and triage begins with asking which one. This covers one core plus configuration as data, the test for whether a difference is data or a capability, and how to tell you have already forked.
- · 9 min read
Index Freshness and Drift: Why a Working RAG System Quietly Goes Wrong
A RAG system that works today degrades quietly as its documents change. There are two kinds of drift: the easy one, where the questions start looking different, and the nasty one, where the questions look identical but the right answer changed underneath. The fix is re-checking on a schedule against a baseline, and never auto-rebuilding when the alarm fires, because half the time it is a data-plumbing break, not a real change.