NUS Libraries announces a new conversational AI platform

- NUS is the first university in the region to develop a proprietary conversational AI platform which supports academic enquiry by drawing on exclusive NUS research and regionally-focused special collections

- AI Sense Maker can generate concise topic summaries, identifying related concepts, curating references for further reading and creating interactive knowledge graphs that show how ideas are connected

- The platform will launch with an initial foundation of 150,000 digitised materials

Source: NUS. Shelves of books and other displays.
Source: NUS. Located on the second floor of NUS’ Central Library, the BookBridge showcases more than 3,000 rare books and artefacts, offering a glimpse into NUS Libraries’ much larger special collections.


The National University of Singapore (NUS) has announced AI Sense Maker (ASM), becoming the first university in Southeast Asia to use conversational AI to transform students and academics’ learning journeys.

Developed jointly by NUS Libraries and NUS Information Technology (NUS IT), AI Sense Maker is a web-based platform powered by OpenAI’s large language model (LLM). Users can begin their research by asking questions in everyday language, such as: “Why do some neighbourhoods in Singapore feel hotter than others?”. This is in contrast with traditional search strategies, where users have to scour different databases separately, and make use of more advanced search methods.

Rather than relying on exact keywords, AI Sense Maker uses semantic search to understand the meaning and intent behind a question, retrieving information based on contextual meaning and user intent rather than literal keyword matches. This allows it to surface relevant sources that may use different terminology, while also identifying related concepts. 

It then generates concise topic summaries, identifies related concepts, curates references for further reading and creates interactive knowledge graphs that show how ideas are connected. This is faster than conventional keyword searches, which return a list of articles that users must open and read individually to understand a topic. Such searches also depend heavily on the terms entered and may overlook relevant materials without the exact keywords.

Associate Professor Natalie Pang, University Librarian at the National University of Singapore said: "Researchers today are not short of information, they are short of time and clarity. AI Sense Maker is designed to help people make sense of information, not simply find it. By connecting ideas across trusted sources, it gives students and researchers a more intuitive starting point for deeper enquiry. Rather than replacing critical thinking, it helps people ask better questions, discover new connections and generate fresh insights."

“As part of our broader Libraries of Fantastic Things innovation framework, AI Sense Maker reflects NUS Libraries’ continued efforts to harness new technologies across research discovery, digitisation and research support, while strengthening the preservation and accessibility of rare and fragile collections.”

The platform will officially launch on 20 August 2026 with an initial foundation of 150,000 digitised materials, drawn from ScholarBank, NUS' repository of research papers, and Digital Gems, NUS Libraries’ ongoing effort to digitise its special collections of rare materials and primary sources with a special focus on Southeast Asia. The rare materials include books dating back to the 17th century.

Comments

Post a Comment

Popular posts from this blog

NVIDIA brings secure agent workspaces and confidential computing to AI factories

As enterprise AI use cases move from chatbots to persistent, autonomous agents capable of reasoning, writing their own software tools, and executing complex cross-system workflows, demands on token generation fundamentally rewrite the enterprise model for security, compliance, infrastructure and cost.  To scale safely, organisations need AI factories  that are built for secure, trusted and efficient AI production. NVIDIA is supporting this trend with new reference architectures for  Secure Agent Workspaces ,  Confidential VMs and Confidential Containers .  Legacy IT security controls — static credentials, network allowlists and standard role-based access — were not designed for autonomous agents, NVIDIA said. Securing an AI factory requires a paradigm shift to runtime-enforced, policy-driven guardrails. Enterprises need secure agent workspaces — persistent, single-user environments accessed via enterprise single sign-on. Secure agent workspaces are governed by...
Read more

Fortinet enhances FortiRecon to align with CTEM framework

Fortinet, the global cybersecurity provider driving the convergence of networking and security, has turned the FortiRecon platform into a comprehensive solution aligned with the continuous threat exposure management (CTEM) framework. The latest release introduces expanded internal attack surface monitoring, adversary-centric dark web intelligence, and security orchestration, all in a unified platform. These enhancements help organisations proactively identify and prioritise real-world exposures, validate risks like an attacker would, and accelerate response. “CISOs and security teams are overwhelmed by growing attack surfaces and an endless stream of unprioritised alerts,” said Nirav Shah, Senior VP of Products and Solutions at Fortinet. “With the latest enhancements to FortiRecon , we’re giving organisations an attacker’s eye view of their internal and external exposures, backed by AI-powered threat intelligence from FortiGuard Labs, real-world validation, and automated response...
Read more

Agnes AI enters global top 10 AI lab rankings

- Agnes AI delivers globally-ranked agentic and image AI performance - Offers cost-efficient AI access for emerging markets - Supports national push to upskill tech professionals Agnes AI, a Singapore-headquartered AI model company that has built and trained its own multimodal foundation models entirely in-house, is now a top-10 lead across three independent AI benchmark rankings.  The company said its proprietary models have entered the global top 10 AI labs ranks. The latest rankings on Claw-Eval and Artificial Analysis follow a top-10 AI labs placement on PinchBench , a globally-recognised agentic model evaluation benchmark. According to the company, it is the first Singapore-born AI model company to enter the global top 10 across these international AI lab rankings. Agnes AI noted the benchmark results also provide independent validation that a Singapore-born AI lab can compete on the same global leaderboards as the world’s most-recognised AI companies. “Singapore’s ...
Read more