vault / mlops / sdk-design.md

SDK design

ML platform 56 words 1 outgoing 1 backlinks

An SDK is an interface for model authors. Sensible defaults reduce repeated configuration, but hiding every detail makes debugging harder. Make the ordinary path small, leave important behaviour inspectable, and write errors that suggest the next action. These are design choices, not evidence that a particular interface is always right.

Read the full example: related post.

LINKS IN THIS NOTE

[[ Model serving ]] A trained model is not yet a service. A shared serving path handles the repeated work around it: authentication, tracing, deployment conventions and orchestration. Keep the supported path narrow and explain failures clearly. The post distinguishes the interface I built...