Amity’s generative AI (GenAI) efforts are spearheaded by its dedicated AI Labs, which focuses on researching, understanding, and applying advanced language models such as OpenAI’s GPT to develop high-value business use cases.
Its innovative work in this field has garnered international recognition. Notably, Amity’s advancements in GenAI were highlighted by Microsoft CEO Satya Nadella during his keynote address at the ‘Microsoft Build 2024’ global developer conference.
At Amity AI Labs, it is committed to pioneering solutions that integrate GenAI into existing SaaS and software products, transforming how businesses operate and deliver value to their users.
The Thai Retrieval Augmented Generation (TRAG) Benchmark is designed to comprehensively evaluate the performance of large language models (LLMs) in understanding and generating human-like responses in the Thai language. This page provides a detailed explanation of the benchmark's structure, evaluation criteria, and scoring methodology.
Enhances the accuracy and speed of document search functionalities. Focuses on improving search algorithms for better information retrieval. Ideal for environments with large volumes of documents. Supports Amity’s mission to make content more accessible and organized.
A refined version of the original search optimizer with improved AI models. Offers more contextual and semantic search capabilities. Suitable for enterprises aiming to scale their document search efficiency. Helps users on Amity platforms quickly find relevant content.
Optimizes Natural Language Queries to interpret user intent more effectively. Translate the complex question into SQL query that would correctly retrieve the data needed to answer the question. Improves user satisfaction by delivering accurate responses. Contributes to Amity’s AI-driven user experience initiatives.
Amity Voice AutoQA Model is designed to automate and enhance the quality assurance process. This model uses advanced AI capabilities to effectively evaluate call transcripts and produce reliable scores. The evaluation involves crucial categories such as Call Handling and Call Closure, along with targeted questions like "How engaging was the conversation?" or "How was the agent's general behavior?"
Automatically summarizes chat interactions after completion. Provides concise and actionable summaries for agent review or archival. Saves time in customer service environments. Streamlines workflows within Amity-powered chat solutions.
Detects emotions in voice input using AI. Identifies tone variations to assess user sentiment. Helps personalize responses or flag sensitive interactions. Enhances human-like interaction on Amity’s voice-enabled products.
Enables real-time voice communication with integrated AI features. Supports live transcription, translation, or emotion detection. Designed for scalability across mobile and web platforms. Forms the backbone of voice services within the Amity ecosystem.
Agentic AI for Deep Data Analysis leverages autonomous AI agents to interpret natural language queries and conduct in-depth analysis using multiple LLMs. It delivers actionable insights and recommendations grounded in expert knowledge, enhancing scalability, accuracy, and industry relevance for strategic decisions across diverse data sources and sectors.
