Canary ak lëndëm jëfandikoo Quiz

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Luy tekki jëfandikoo kanari?
   • Routing pursàntaas bu ndaw ci trafik bi ci versioŋ bu bees bi nga koy saytu
   • Yonnee bépp trafik ci xeetu bees bi ci saasi
   • Doxal versioŋ bu bees bi ci njeexte ayu-bis yi kese
   • Deployment te kenn duko saytu
2. Lan mooy màndarga bi gëna am solo ci dugal lëndëm?
   • Genn-wàll jëfandikukat yi lañu jox tontu yi
   • Dafay jot trafik mirrored waaye tontu yi dañuy sànni, duñu ko wane jëfandikukat yi
   • Du dox ludul ci environmaa developpement
   • Dafay wecci xeetu liggéey bi ci saasi
3. What does a shadow deployment protect users from, and what can it still cost?
   • It uses no extra resources and cannot access user data
   • Its predictions are returned to every user
   • Candidate responses are withheld, but mirrored inference still consumes compute and needs side-effect controls
   • It guarantees the candidate has no production impact of any kind
4. How does user-facing traffic differ between a canary and a shadow?
   • Both always send candidate output to every user
   • A shadow deployment never uses production inputs
   • A canary is only an offline test
   • A canary serves candidate responses to a defined live-traffic segment; a shadow typically does not
5. What should a team define before starting a canary or shadow rollout?
   • Traffic rules, monitoring thresholds, rollout duration, and a rollback owner
   • A promise that the candidate will outperform production
   • A fixed traffic percentage that must never change
   • A requirement to expose every user to the candidate
6. naka la deployment canary ak shadow di delloo seen biir?
   • Benn mbir lañu, te wuute ci seeni tur
   • Shadow dafay saytu jeffin ci trafik bi ci saasi te jëfandikukat bi du am benn risk; canary dafay saytu njeextalu jëfandikukat bi ci dagg bu ndaw
   • Canary dafay sànni tontu yi ci diir bi lëndëm di leen dimbali
   • Amul benn ci ñoom lu jëm ci dem bi ak dikk bi
7. What should an operator do before mirroring production requests to a shadow model?
   • Allow the shadow model to execute writes twice
   • Assume copied requests contain no sensitive data
   • Isolate side effects and protect the handling of copied request data
   • Disable all monitoring of the candidate
8. What does a canary reveal that a shadow deployment does not directly measure?
   • Whether candidate inference consumes compute
   • How its predictions compare offline
   • Whether a model can load in the serving stack
   • How the candidate affects users who are actually served by it