Interview practice
AI Architect Practice Arena
LLM-as-judge mock interviews — 35 playbook questions, dual grading.
Sectioned system-design forms, STAR behavioral practice, and reasoning trade-offs — graded by OpenAI and Anthropic against Staff+/Principal rubrics. Bring your own API key; keys never touch our servers.
In one sentence
Mock system design and behavioral interviews with dual LLM judges.
Decision
Per-question rubrics over generic chat — grading matches playbook depth.
Measured signal
139/140 live cases passed · judge disagreement shown, not averaged away.
Honest limitation
Requires user's OpenAI or Anthropic API key; no server-side key storage.
- 35/35 interview playbook coverage across three rubric formats
- Dual-judge grading with disagreement surfaced as trust signal
- 139/140 live calibration cases passed across two independent runs
- BYOK architecture — zero org-side API cost at any scale
Architecture diagram
Next.js · Vercel · OpenAI · Anthropic APIs