
This project is an AI-driven interview preparation platform combining agent-based orchestration and web tooling. CrewAI agents (agent1/agent2) run task-driven workflows that use tools for curriculum access, web research, and database storage. A FastAPI backend orchestrates kickoff routes and coordinates asynchronous agent execution. LLM integration is provided via litellm/Fireworks, with provider-specific handling for request compatibility. The frontend (Vite + React) hosts session UIs and authentication, while backend utilities seed and manage the database. Tests cover curriculum, database, and web access components. The system aims to generate targeted practice sessions, quizzes, and evaluative feedback tailored to role, topic, and skill level.
13 Jul 2026