Multi-agent AI system for interview practice. Features adaptive questioning, real-time coaching, personalized feedback, and learning recommendations via web search. Built with FastAPI, React, LangChain, and Google Gemini. Deployed on Azure & Vercel.
# AI Interviewer Agent 🚀 [](httpss://opensource.org/licenses/MIT) The **AI Interviewer Agent** is a sophisticated, AI-powered platform designed to help users practice and excel in job interviews. It leverages a multi-agent system to provide a realistic, interactive, and adaptive interview experience, complete with real-time coaching, in-depth performance analysis, and personalized learning recommendations. The frontend is a sleek, modern single-page application built with React and Vite, designed for an intuitive user experience and deployed on **Vercel**. The powerful backend is a FastAPI application, containerized with Docker and deployed on **Microsoft Azure**, ensuring scalability and reliability. --- ## ✨ Core Features This platform is more than just a Q&A bot. It's a comprehensive interview preparation ecosystem. ### 1. Dynamic AI Interviewer Agent - **Adaptive Questioning**: The AI interviewer doesn't just follow a script. It generates relevant questions based on the job role, job description, and the content of your resume. It also asks insightful follow-up questions based on your answers. - **Multiple Interview Styles**: You can choose from various interview styles (`Formal`, `Casual`, `Technical`, `Aggressive`) to simulate different real-world scenarios. - **Configurable Difficulty**: Adjust the interview's difficulty (`Easy`, `Medium`, `Hard`) to match your preparation level. - **Time-Aware Sessions**: Practice under pressure with timed interviews, forcing you to give concise and effective answers. ### 2. Real-time Agentic Coach - **Turn-by-Turn Feedback**: As you answer each question, a silent "Coach Agent" analyzes your response in the background. It provides immediate, private feedback on your clarity, confidence, and the substance of your answer. - **In-depth Performance Metrics**: The coach tracks various aspects of your performance throughout the session. ### 3. Persona
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.