incident #003·class feedback quality·status resolved
> the problem
Interview prep is mostly static question banks — no questions tailored to your role, and no feedback until a mentor has time for you.
> the approach
Simulate a real interview: generate role-based questions with an LLM, evaluate the answers, and hand back specific, instant feedback — no mentor required.
> architecture.log
01INFORole-based question selection drives prompt construction
02INFOGoogle Gemini generates questions and grades responses
03INFOPostgreSQL persists sessions, answers, and feedback history
04INFONext.js front end for the interview flow
error · root cause
Getting the model to produce consistent, useful evaluation instead of vague praise — structuring prompts and schemas so feedback is specific and actionable.
info · resolution
A model is only as good as the structure around it. Constrain generation and grading with clear schemas and role context and the quality jumps.