interview

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

Removing software-interview assumptions to support interview practice across professions

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

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

How interviewer personas moved from a selection UI into distinct interview and study flows

Connecting interview results to topic progress, review timing, and the practice loop

Provider boundaries, latency handling, and failure modes that surfaced while wiring Gemini and Ollama into the same product