🤖 AI-powered CRM assistant using Google Gemini & LangGraph for intelligent lead management
# 🤖 AI-Powered CRM Assistant [](https://www.typescriptlang.org/) [](https://nodejs.org/) [](LICENSE)  An intelligent CRM automation system that uses **Google Gemini AI** and **LangGraph** to analyze leads from amoCRM and provide actionable insights via Telegram. Features a human-in-the-loop architecture to ensure critical business decisions remain under manager control. ## ✨ Key Features ### 🧠 AI-Powered Analysis - **LangGraph Workflows**: Multi-step reasoning chains for complex lead analysis - **Batch Processing**: Efficient analysis of multiple leads simultaneously - **Smart Filtering**: Identifies high-priority leads that need attention - **Risk Scoring**: Calculates deal loss risk based on activity patterns ### 📱 Telegram Integration - **Interactive Cards**: Rich action proposals with approve/reject buttons - **Natural Language Commands**: Understands plain text like "show hot leads" - **Real-time Notifications**: Instant alerts for critical situations - **Command Dashboard**: `/today`, `/hot`, `/risk`, `/stats` and more ### ⏰ Automated Reporting - **Morning Digest** (9:00 AM): Daily overview of tasks and priorities - **Evening Report** (6:00 PM): End-of-day summary - **Weekly Overview** (Monday 10:00 AM): Week-in-review statistics ### 🔐 Human-in-the-Loop - Manager approval required for all CRM actions - Complete audit trail of all AI decisions - Configurable risk thresholds and business rules ### 💾 Persistent Storage - SQLite database for lead scores and action history - Tracks score trends over time - Searchable decision logs --- ## 🏗️ Architecture ![Generated Image January 04, 2026 - 3_42PM](https://github.com/user-attachments/assets/
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.