llm

A system design practice note on separating real-time LLM serving from asynchronous feedback collection at 20K peak TPS

Aligning Kovill’s reply style, question progression, and language with product-owned state

Evaluating full interview conversations with a typed LLM-as-a-Judge pipeline

Recovering interview control flow lost during a prompt and grounding refactor

Enforcing LLM cost limits in the backend and modeling their operational impact

Treating active sessions as resumable work while preserving truthful progress

A Tail Villain note on treating LLM completion signals as advisory instead of letting them end sessions unconditionally

A Tail Villain note on study telemetry and the move toward a roadmap-level interview hub