Where developers grow together

Lively: The Real-Time Voice AI Sales Agent

Lively is a real-time voice AI sales agent built to handle sales conversations the way a strong salesperson would, by listening, understanding, remembering and adapting. Instead of following a fixed script, Lively maintains a live Deal State containing the customer's needs, budget, users, buying intent, objections and decision-makers. It can retrieve product information, handle interruptions and changing requirements, qualify leads, book demos, update CRM records and escalate to a human with full context. Built on Agora Conversational AI, Lively turns a natural voice conversation into a measurable sales outcome, from the first question to the next action.

EchoSphere – AI Voice Sales Agent for Car Dealerships

EchoSphere is a real-time AI voice sales agent built for car dealerships, designed to solve a simple but costly problem: not every walk-in customer gets attention when staff are busy, leading to lost leads and inconsistent pitches.With EchoSphere, a customer scans a QR code to start an instant, natural voice conversation with an AI assistant — no app download needed. The AI understands their budget and preferences, pulls live inventory data to recommend the best-matching car alongside a competitor comparison, and can offer pre-approved discounts within dealership-set rules. As the conversation progresses, it scores buyer intent in real time, and once a customer is ready to buy, automatically hands off a full summary to a human salesperson — so every lead is captured and every closer walks in prepared.Built using Agora's Conversational AI voice engine, a FastAPI backend, PostgreSQL/Supabase for data, and a React + Tailwind frontend, with a retrieval-based (RAG) layer ensuring every recommendation is grounded in real, current inventory.Built by Team Breeze the Builders for Agora Hackathon 2026.

SHRAVYA AI-Powered live Interview Panel

Shravya — Three AI Experts. One Intelligent Interview. Shravya is a voice-native, multi-agent AI interview platform built around Agora’s real-time communication infrastructure. It brings together three specialist AI interviewers—a System Architect, a Product Manager, and a Security Lead—to evaluate candidates through a shared, adaptive conversation. Each agent contributes a distinct perspective, while an orchestration layer manages context and speaking turns. Its defining innovation is intra-panel friction: agents can challenge one another’s priorities and ask candidates to resolve real-world trade-offs. When a candidate proposes a complex architecture, the System Architect examines scalability, the Product Manager questions delivery timelines, and the Security Lead investigates vulnerabilities. This creates opportunities to assess technical depth, practical judgment, and decision-making. Through live voice-to-workspace synchronization, the panel also follows code and architecture diagrams as candidates work. Changes in the shared workspace inform follow-up questions, connecting what candidates explain with what they actually build. Interruption handling is designed to keep the conversation natural and responsive. After the interview,  assessment engine links competency scores and feedback to timestamped transcript and audio evidence. Recruiters can review the reasoning behind each assessment and retain responsibility for the final hiring decision. Shravya aims to make expert interviews available on demand, reveal how candidates reason, and give hiring teams evidence they can inspect.