ResoluteAI

Sci-Bot is an AI-powered research assistant built on top of Sci-Hub, designed to answer user questions by directly searching and analyzing scientific literature instead of generating responses from general training data. It works by scanning a vast database of full-text academic papers and extracting relevant findings to produce answers grounded in published research, often including references and links to the original studies. It presents itself as a simple interface where users can ask questions in multiple languages, and the system automatically searches for relevant keywords, retrieves academic articles, and synthesizes information into a structured response. It follows a step-by-step process similar to a human researcher, showing intermediate searches and sources before delivering a final answer. A key focus is on reducing hallucinations by relying on existing scientific papers rather than purely generative outputs, and it can provide direct access to full-text documents.

Iris.ai is a world-leading and award-winning AI engine for scientific text understanding. It is a comprehensive platform for all research-related knowledge processing needs. Our Researcher Workspace solution provides smart search and a wide range of smart filters, reading list analysis, auto-generated summaries, autonomous extraction, and systematising of data. Iris.ai allows humans to focus on value creation by saving 75% of a researcher’s time, doing specialised, interdisciplinary field analysis to an above human level of accuracy. Its algorithms for text similarity, tabular data extraction, domain-specific entity representation learning, and entity disambiguation and linking measure up to the best in the world. Its machine builds a comprehensive knowledge graph containing all entities and their linkages to allow humans to learn from it, use it, and give feedback to the system. Applying these features to scientific and technical text is a complicated challenge few others can achieve.