| # Trust-First AI Copilot | |
| **Perplexity-Style • System-Driven • No Custom LLM** | |
| Deployed Link: https://trust-first-ai.vercel.app/ | |
| A trust-first AI Copilot that delivers **verified, source-grounded, and confidence-scored answers** using strict system rules — inspired by Perplexity and designed to fix the core limitations of modern AI copilots. | |
| --- | |
| ## Problem | |
| Most AI copilots today: | |
| - Produce confident but incorrect (hallucinated) answers | |
| - Lose context in long or multi-file documents | |
| - Hide sources and assumptions | |
| - Provide limited admin visibility and control | |
| - Encourage blind dependency on AI outputs | |
| These issues lead to **wrong decisions, rework, and low trust**. | |
| --- | |
| ## Solution | |
| This project implements a **system-first AI Copilot** where: | |
| - Retrieval is mandatory (no context → no answer) | |
| - Every answer is backed by sources | |
| - Confidence is explicitly shown | |
| - Low-confidence answers are refused | |
| - Automation is human-approved | |
| - Security, transparency, and auditability are built-in | |
| The focus is **system design over model size**. | |
| --- | |
| ## Core Principles | |
| - No guessing | |
| - No hidden sources | |
| - No blind automation | |
| - Refusal is a feature, not a failure | |
| --- | |
| ## Key Features | |
| - Mandatory Retrieval-Augmented Generation (RAG) | |
| - Source-linked answers with citations | |
| - Confidence scoring (High / Medium / Low) | |
| - Automatic refusal on insufficient data | |
| - Workspace / project-level context memory | |
| - Intent detection and auto-clarification | |
| - Human-in-the-loop automation (n8n) | |
| - Zero-trust data access | |
| - Full audit logs (OpenTelemetry) | |
| - Model-agnostic LLM layer (Groq) | |
| --- | |
| ## System Architecture | |
| User | |
| → Intent Detection | |
| → Search & Retrieval (Tavily + Vector DB) | |
| → Context Ranking & Filtering | |
| → LLM (Groq – language & reasoning only) | |
| → Verification & Confidence Engine | |
| → Answer + Sources + Assumptions | |
| → (Optional) Human-Approved Automation | |
| → Audit Logs & Admin Dashboard | |
| ## What This Project Is Not | |
| - Not a chatbot | |
| - Not prompt-dependent | |
| - Not blind AI | |
| - Not a Copilot replacement | |
| This is a **controlled, transparent, enterprise-ready AI system**. | |
| --- | |
| ## Tech Stack | |
| **Frontend** | |
| - Next.js | |
| - React | |
| - Tailwind CSS | |
| **Backend** | |
| - FastAPI (Python) | |
| **AI & Data** | |
| - LLM: Groq (LLaMA / Mixtral) | |
| - Search: Tavily API | |
| - Embeddings: Hugging Face / Local models | |
| - Vector DB: FAISS / Qdrant | |
| - Automation: n8n | |
| - Logging & Audit: OpenTelemetry | |
| **Deployment** | |
| - Frontend: Vercel | |
| - Backend: Render | |
| --- | |
| ## Project Structure | |
| project-root/ | |
| ├── frontend/ | |
| │ ├── pages/ | |
| │ ├── components/ | |
| │ └── services/ | |
| ├── backend/ | |
| │ ├── main.py | |
| │ ├── rag/ | |
| │ ├── verification/ | |
| │ ├── automation/ | |
| │ └── requirements.txt | |
| ├── docs/ | |
| └── README.md | |
| yaml | |
| Copy code | |
| --- | |
| ## Required API Keys | |
| | Service | Purpose | | |
| |-------|---------| | |
| | Groq | LLM inference | | |
| | Tavily | Web search | | |
| | Hugging Face | Embeddings | | |
| | n8n | Automation | | |
| > All API keys are stored **only in backend environment variables**. | |
| --- | |
| ## Local Setup (Backend) | |
| ```bash | |
| git clone https://github.com/your-username/your-repo.git | |
| cd backend | |
| python -m venv venv | |
| source venv/bin/activate | |
| pip install -r requirements.txt | |
| Create .env: | |
| env | |
| Copy code | |
| GROQ_API_KEY=xxxx | |
| TAVILY_API_KEY=tvly_xxxx | |
| HF_API_KEY=hf_xxxx | |
| N8N_API_KEY=xxxx | |
| N8N_BASE_URL=http://localhost:5678 | |
| Run backend: | |
| bash | |
| Copy code | |
| uvicorn main:app --reload | |
| Local Setup (Frontend) | |
| bash | |
| Copy code | |
| cd frontend | |
| npm install | |
| npm run dev | |
| Deployment | |
| Backend | |
| Push code to GitHub | |
| Connect repository to Render | |
| Build command: | |
| bash | |
| Copy code | |
| pip install -r requirements.txt | |
| Start command: | |
| bash | |
| Copy code | |
| uvicorn main:app --host 0.0.0.0 --port 10000 | |
| Frontend | |
| Deploy via Vercel | |
| Set backend API URL in environment variables | |
| Security & Trust Model | |
| API keys never exposed to frontend | |
| Per-user data isolation | |
| Role-based access control | |
| Full audit trail for AI actions | |
| How Hallucinations Are Prevented | |
| Retrieval is mandatory | |
| Claims must map to sources | |
| Confidence is evaluated | |
| Low confidence triggers refusal | |
| No source → No answer | |
| Use Cases | |
| Research and academic assistance | |
| Enterprise internal knowledge copilots | |
| Policy and compliance analysis | |
| Long-document summarization | |
| Decision-support systems | |
| Future Improvements | |
| Offline read-only mode | |
| Multimodal reasoning (charts + text) | |
| Advanced admin dashboards | |
| Domain-specific copilots | |
| Final Note | |
| LLMs don’t fail — systems fail. | |
| This project demonstrates how strong system design beats larger models. | |