Sample Solutions
Document Intelligent Multi-Agent System (DIMS)
Client Service Agent
CRM Agent
Receptionist Agent
Language Learning Support Agent
Agentic Vision AI Agent
Testing Agent
Patient Intake Assistant
Note Taker Agent
Client Order Assistant
Warehouse Management System (WMS) AI Agent
Multi-taskers Agent
Description
Document Extraction AI Agent automates the processing of complex paperwork by extracting structured data from contracts, forms, invoices, and medical records. With built-in error detection, system integration, and support for both scanned and digital documents, it streamlines workflows for high-volume, document-heavy organizations.
Functions
- Extract structured data from unstructured/complex documents (contracts, forms, invoices, medical records)
- Automatically map data into ERP, CRM, or custom systems
- Built-in error detection and correction suggestions
- Support for scanned images and digital documents
Technologies
- AI: LangChain, LangGraph, AI Agent, Multi-Agent, Agentic Automation, MCP, OpenAI, Gemini.
- BE: Python - FastAPI.
- FE: React - Next JS, TailwindCSS v4, TanStackQuery, Zustand.
- Database & Storage: MongoDB, Redis, PostgreSQL, MindsDB, MinIO.
- Others: Kafka, Flink, Langfuse.
Description
An AI assistant that responds to client questions in real-time. It learns from your documents, is easy to set up with a drag-and-drop interface, and works seamlessly across your website and social media channels
Functions
- Ingest knowledge from multiple data sources (web, text, doc, PDF, internal systems)
- Route complex cases to the right human agents with full conversation history and client data
- Track client satisfaction and emotional tone for continuous improvement
- Analyze queries and preferences to suggest relevant products or services in real time
- Provide instant translation for multilingual, global client support
- Integrate across websites and social media channels (Facebook, Telegram, TikTok, Zalo, etc.)
Technologies
- Front-end: Next.js, CopilotKit, Tailwind CSS
- Back-end: FastAPI, LangGraph, PostgreSQL, LightRAG
- Infrastructure: Docker
- LLM models: Qwen3, OpenAI
Description
A CRM application that streamlines the entire customer journey — from initial enquiries and contacts to full customer conversion — enhanced with AI-powered automation flows to improve efficiency, engagement, and decision-making.
Functions
- Centralized management of leads, contacts, and customer data
- AI-powered automation of sales and marketing workflows
- Intelligent lead scoring and prioritization
- Automated follow-ups and personalized communication
- Customer journey tracking from enquiry to conversion
- Data-driven insights for improved decision-making
- Integration with multiple communication channels (email, chat, social media)
- Performance analytics and reporting for sales and marketing teams
Technologies
- AI techniques: Lovable, n8n, Cursor AI
- LLM: Google Gemini, Ollama, OpenAI Whisper, Hugging Face, RAG
- ReactJS / NodeJS
- PostgreSQL, Qdrant
Description
Receptionist Agent streamlines corporate front-desk operations with automated visitor check-in, real-time face and voice recognition, and instant interviewee registration with HR notifications. It also supports on-the-spot visitor badge printing for a faster, more professional welcome experience.
Functions
- Visitor check-in automation
- Real-time face and voice recognition
- Interviewee registration and notification to HR/interviewers
- Visitor badge printing
Technologies
- AI techniques: Pytorch, OpenCV, Speech-to-Text, Text-to-Speech, AI Lip Sync
- LLM: Google Gemini, RAG
- Streaming media: WebRTC, SRS
- Backend: Python, FastAPI
- Frontend: ReactJS
Description
An AI-powered language learning platform that develops language skills through a personalized learning journey, context-aware roleplay practice with instant feedback, and an AI tutor acting as a language coach to guide learners at every step. Its interactive dashboard tracks progress, making learning engaging, tailored, and effective for all proficiency levels.
Functions
- Smart assessment test
- Personalized learning journey
- AI Roleplay Practice with Instant Feedback
- AI Tutor & Language Coach
- Learning dashboard and progress tracking
Technologies
- AI: Open AI, LangChain, Azure Speech, TTS, STT, Whisper, Heygen Avatar, Python, Fast API
- BE: C# .NET, Umbraco
- DB: SQL Server, Mivus Vector DB
- FE: Mico-Frontent with Angular, ReactJS, PrimeNG, HTML, CSS, JavaScript
Description
Safety & Security Monitoring AI Agent safeguards factories, warehouses, and logistics hubs with real-time IoT monitoring, AI-driven pattern recognition, and instant alerts for threats or rule violations. It integrates with access control and emergency protocols to ensure a safer, more secure working environment.
Functions
- Real-time monitoring via IoT devices (CCTV, sensors, robots, AGV)
- Automatic alerts for rule violations or threats (fire, intrusion, machine errors)
- AI-based pattern recognition for unusual behaviors
- Integration with access control and emergency protocols
Technologies
- AI Frameworks: Vision-Language Model, GPT- 4v
- Video Streaming: NVIDIA DeepStream, NVIDIA NIM, NVIDIA NeMo
- Edge AI: Jetson Orin
Description
This Agent can create test cases from user stories, simulate manual testing steps, and write automation scripts. This Agent can adapt to system changes with self-healing capabilities, reducing the need for constant test maintenance.
Functions
- Generate test cases from story: Automatically create test cases from user stories
- Mimic manual testing execution: Perform clicks, data entry, and navigation like a real tester
- Simulate automation scripting process: Write test scripts without manual coding
- Self-healing/maintenance: Adapt to UI changes automatically
Technologies
- Front-end: React, Next.js, TailwindCSS
- Back-end: Spring Boot, FastAPI
- Infrastructure: MinIO, PostgreSQL, Redis, Kafka, Keycloak, Kubernetes
- AI/LLMs: LangChain, LlamaIndex, Claude, OpenAI
Description
This solution simplifies patient check-ins and provides clear guidance. It also integrates with HIS, EMR, and scheduling systems for better coordination.
Functions
- Symptom input via text or image: Patients can submit symptoms by typing or uploading photos
- Medical AI understanding: Analyze inputs using trusted medical datasets for accurate assessment
- Clear health guidance: Deliver easy-to-follow advice based on symptom analysis
- System integration: Connect with HIS, EMR, and scheduling systems for updates and bookings
Technologies
- TMA Data Platform
- TMA Agentic AI Framework
- Gemini
Description
Note taker agent boosts office productivity by automatically transcribing meetings, highlighting action items, decisions, and deadlines, and recognizing multiple speakers with clear labeling. It seamlessly exports notes to documents or project management tools for easy follow-up and collaboration.
Functions
- Auto-transcription of meeting recordings
- Highlight action items, decisions, and deadlines
- Multi-speaker recognition and labeling
- Export to docs or project tools
Technologies
- Backend: Go (Golang) with Gin Framework
- Frontend (Desktop): .NET 8 (WPF / WinForms)
- Speech-to-Text (STT): Google STT, Azure Speech, AWS Transcribe, Gemini, Whisper (Self-Hosted)
- LLM (Summarization): Google Gemini, OpenAI GPT
Description
An AI agent chatbot integrated across web and social channels to automate product queries, confirm purchases, and track orders - enhancing the full client journey.
Functions
- Sales assistant: Help clients find products, order, and get answers
- Auto order creation: Create orders instantly via system integration
- Auto handoff: Switch to a human agent when needed
- Easy integration: Integrate to websites and social platforms
Technologies
- Multi-agent framework: ADK, A2A, MCP
- AI & LLM models: OpenAI, Google AI
- Embedding models: OpenAI embeddings model, Google AI embedding model
- Backend layer: Python, FastAPI
- Database & storage: MongoDB, MinIO
Description
The current Warehouse Management System (WMS) requires warehouse staff and managers to go through multiple steps to retrieve information or complete simple tasks. The AI Agent is designed to streamline these processes by enabling instant searches, delivering real-time reports, and significantly improving operational efficiency. This solution also lays the foundation for predictive analytics and automation in future phases.
Functions
- Query inventory by SKU or product description.
- Retrieve storage location information for goods.
- Check the status of inbound and outbound orders.
- Generate quick reports (e.g., top SKUs by stock quantity, SKUs running low).
Technologies
- AI techniques: ORC, Speech-to-Text
- LLM: Google Gemini
- Backend: Python, FastAPI
- Frontend: ReactJS
Description
Multi-taskers Agent connects homeowners and independent workers through a smart platform for creating, posting, and managing home tasks. With AI-powered matching, secure bidding, and built-in task tracking, scheduling, and ratings, it ensures fast, transparent, and efficient service delivery from start to finish.
Functions
- Create, post, and manage home tasks
- Smart matching and bidding system for taskers
- Support for task tracking, scheduling, and rating
- Secure chat and negotiation interface
Technologies
- AI techniques: Lovable, n8n, Cursor AI
- LLM: Google Gemini, Ollama, OpenAI Whisper
- ReactJS / NodeJS
- PostgreSQL
