Ming, featuring realtime voice chat, live sentiment analysis, and a detailed scenario overview.
🏆 First-Place Winner — Best use of Google Gemini (MLH) at HackGT 2025
Ming is an AI-native, multi-agent L&D platform that transform current and aspiring engineer to managers via practicing real-world workplace scenarios (performance reviews, conflict resolution, even layoffs) through LLM-driven role-play with detailed analysis and actionable feedback.
- Bridge technical → managerial: Upskill engineers into empathetic, effective managers—faster and more affordably than hiring externally.
- Soft-skills that scale: High-quality practice for communication, coaching, and conflict resolution—skills traditional trainings rarely teach well.
- AI-economy ready: As automation reshapes work, Ming helps people build durable, human-centered competencies.
- Role-played conversations with LLM NPCs across tricky scenarios (reviews, conflicts, reorganizations, exits).
- Real-time voice & signals: Live sentiment analysis, pacing, interruptions, and conversational grounding.
- Deep debriefs: Annotated transcripts, strengths/areas to improve, and personalized follow-ups.
- Adaptive curriculum: New scenarios are generated from each user’s performance profile.
Our analysis page, with an annotated transcript, summary, and voice-integrated chat to receive further feedback.
- Frontend: Next.js (App Router) + React, Tailwind, shadcn/ui
- Orchestration: CedarOS to integrate frontend with multi-agent runtime
- Backend: Mastra connected to Google Gemini (LLM + Sentiment Analysis)
- Infra: Deployed full-stack to Cloudflare, hosted on our own domain
- Architecture: Multi-agent LLMs coordinate roles (manager, employee, facilitator/coach) for realistic dynamics
Prereqs: Node 20+ and npm
# 1) Install root deps
npm i
# 2) Install backend deps
cd src/backend
npm i
# 3) Back to project root
cd ../../
# 4) Run dev servers
npm run devEnvironment variables (example):
GOOGLE_GENERATIVE_AI_API_KEY, andNEXT_PUBLIC_GOOGLE_GENERATIVE_AI_API_KEY— required for LLM + sentimentOPENAI_API_KEY, — for real-time STT and TTSNEXT_PUBLIC_URL*— (optional) for connecting Frontend to Mastra Backend in production by providing Mastra Backend URL
- 🎭 Multi-agent scenarios with realistic personalities and constraints
- 🗣️ Realtime voice (speak to the NPCs; they speak back)
- 📈 Live sentiment & signals to nudge pacing and tone
- 🧠 Strengths/weaknesses modeling → personalized next scenarios
- 📝 Annotated transcripts with feedback and targeted micro-lessons
- ⚙️ Pluggable scenarios (JSON/YAML) for custom org content
- Cloudflare production split: We initially bundled Next.js and the Mastra server into a single Wrangler target, then split into two services and pointed the Next.js server to Mastra—stabilizing deploys and edge runtime behavior.
We want to help people learn and build skills that endure. Technical orgs need more managers who combine deep engineering instincts with excellent people leadership. Traditional trainings are generic and forgettable; Ming aims to be hands-on, adaptive, and effective.
- UI: Next.js, React, Tailwind, shadcn/ui
- AI/Agents: Mastra, Google Gemini (LLM + Sentiment)
- Orchestration: CedarOS
- Infra: Cloudflare (Workers/Pages), custom domain
- 🧪 Stakeholder pilots & usability testing
- 🕊️ Multi-party conversations (e.g., mediating conflict between two coworkers)
- ⚡ Ultra-low-latency agent interactions
- 🥽 Immersive AR/VR practice environments
- 📱 Seamless mobile support
- 🔎 Culture-aware scaling: learn patterns within a company to tailor coaching
- Major League Hacking (MLH) — Best use of Google Gemini Prize (HackGT 2025) 🏅
- Thanks to mentors, judges, and early testers for feedback!