Zendy Launches ZAIA, a Domain-Specific AI Assistant
Dec 15, 2023 |
4 Mins ReadUnited Arab Emirates, 15 December 2023 - AI-powered research library, Zendy, announced the launch of its AI Assistant, ZAIA, a domain-specific Large Language Model (LMM) developed by Zendy’s data science team.
ZAIA (short for Zendy AI Assistant) exists to help researchers quickly understand key research concepts and discover research papers that specifically link to inputs. These two functions enhance the efficiency and effectiveness of the literature review process.
You can ask any research-related question, and ZAIA will analyse millions of academic research papers to give you credible answers backed by references.
Unlike general-purpose language models, ZAIA is trained with Zendy’s own data. In the future, it can also query, in real-time, additional sources from publisher data that are not available on the public domain.
There is growing recognition of the necessity for domain-specific solutions to strengthen the credibility of data. Fine tuning models on domain-specific data narrows down the LLM’s focus to improve performance in a defined context, thus reducing the likelihood of hallucinations.
“We developed ZAIA to advance the usage of AI on research platforms and improve the research discovery process for researchers. ZAIA aims to assist readers on Zendy by quickly solving research-related questions. ZAIA stands out from other AI products as it is fed real-time data and information available on Zendy, which is then fine-tuned to efficiently cater to our users,” said Zendy’s Head of Technology, Rodrigo Pinto.
“The first iteration of our LLM, ZAIA, is our unique AI offering for Zendy users who can now leverage the best of AI to improve their research discovery process. This is a very exciting milestone for Zendy and we look forward to the feedback from our valued users,” said Zendy Co-founder Kamran Kardan.
Committed to helping foster an ecosystem of collaborative partnerships rooted in responsible AI practices, Zendy’s Large Language Model is built to be entirely customisable. It has the capacity to learn from diverse datasets with integration made simple through Restful API’s or Websocket APIs.
“Bigger picture, our technology presents limitless potential for organisations and institutions yet to integrate the power of LLMs into their workflows. The potential is immeasurable, with use cases including on-demand tutoring, psychology support services, employee onboarding, the list goes on,” continued Kamran Kardan.
To find out more about Zendy’s AI solutions email hello@zendy.io.
You can use ZAIA now on Zendy. To access, log in or sign up to Zendy: www.zendy.io.
We Are Exhibiting UKSG 2025 Annual Conference & Exhibition in Brighton!
We're thrilled to announce that we will be exhibiting at the 48th UKSG Conference from March 31 to April 2, 2025, in Brighton, UK. Visit us at booth #79 to experience: Live Demonstrations: See how Zendy’s AI-powered tools, like ZAIA and AI Summarisation, can streamline your research with reference-backed answers to all your research questions and concise summaries of complex academic papers Personalised Consultations: Meet our team to discuss how Zendy can support your library’s digital transformation. Interactive Sessions: Learn about our affordable subscription models and global accessibility initiatives. Meet Kamran Kardan, Sara Crowley Vigneau and Lisette van Kessel to learn how Zendy is making knowledge more accessible and affordable for researchers, students, and professionals worldwide. Don't miss this opportunity to explore the future of scholarly communication. To schedule a meeting with our team, please email us at info@zendy.io About UKSG Annual Conference: The UKSG Conference is a premier event in scholarly communications, attracting global delegates including librarians, publishers, researchers, and students. It offers an excellent platform for networking and exploring the latest trends in the research and publishing community. To learn more visit: https://www.uksg.org/events/conference25/ .wp-block-image img { max-width: 50% !important; margin-left: auto !important; margin-right: auto !important; }
We are Attending the 20th Annual Electronic Resources & Libraries (ER&L) Conference
We’re excited to announce that we will be attending the 20th Annual Electronic Resources & Libraries (ER&L) Conference from March 23–26, 2025, in Austin, Texas! This milestone event brings together professionals in e-resources, digital services, and the library industry to share insights, foster innovation, and build connections. Let’s Connect! If you’re attending ER&L 2025 or will be in Austin during the event, set up and schedule a meeting with our Co-founder Kamran Kardan. Please email us at info@zendy.io to schedule a time to discuss ZAIA’s vision for the future of AI in research and digital innovation. About ER&L 2025 The ER&L Conference is a community-driven event celebrating its 20th year of bringing together professionals passionate about electronic resources and digital services. With a peer-reviewed program shaped by industry experts, it’s the perfect space to explore trends, technologies, and solutions shaping the future of libraries. Location: Austin, USADates: March 23–26, 2025 Join us as we celebrate two decades of innovation in e-resources management! We look forward to seeing you there! To learn more visit – https://electroniclibrarian.org .wp-block-image img { max-width: 85% !important; margin-left: auto !important; margin-right: auto !important; }
Announcing our RAG-Based Revenue-Sharing Model for Academic Publishers
We are excited to announce a first-of-its-kind revenue-sharing model for AI-generated content, ensuring that publishers are fairly compensated when their paywalled research is cited by AI. Zendy Co-founder Kamran Kardan Our domain-specific large language model (LLM), ZAIA, uses Retrieval-Augmented Generation (RAG) to retrieve data from a diverse collection of open access (OA) and paywalled metadata through licensing agreements with publishers. Based on reference generation by the LLM, our new revenue-sharing model enables a fair and sustainable approach to compensating academic publishers for the use of their content by AI. Empowering Publishers with AI Innovation For years, major academic publishers have been cautious about AI companies using their research, citing copyright concerns, revenue impact, and the need for proper attribution. Our new model introduces a transparent, ethical approach for publishers to monetise their content in the AI era. Many large language models are restricted to training on publicly available research, as major publishers have not yet actively licensed their work to AI companies. Our revenue-sharing model is one of the first of its kind, ensuring clear consent, proper attribution, and fair compensation based on content retrieval. The transparent revenue-sharing mechanism ensures fair compensation for publishers based on the number of references provided in ZAIA’s responses. Our co-founder, Kamran Kardan, said: "This is a positive shift for the academic publishing industry. For the first time, AI is being used to drive revenue back to publishers instead of bypassing them. Ethical AI also means giving credit—and compensation—where it’s due. In the long term, we believe even authors should share in this revenue." We are partnering with a range of international publishers on this model, including IT Governance, Lexxion, British Online Archives, and Lived Places Publishing. Additionally, the RAG model is available for open access publishers, and we are currently exploring alternative compensation models for open access. A Leap Forward for Researchers and Institutions ZAIA provides users with precise, contextually relevant content tailored to their research needs. It offers answers to researchers' questions with reference-backed responses, ensuring that researchers and institutions can access high-quality, peer-reviewed materials while supporting the publishers who produce them. Promoting Sustainable and Ethical AI Content Partnerships To deliver accurate, unbiased, and comprehensive insights, large language models (LLMs) require diverse academic content. Our RAG-based model encourages broader collaboration between publishers and AI companies, fostering ethical agreements rooted in mutual licensing. Direct licensing with publishers allows us to guarantee high-quality, accurate, and up-to-date content, including retractions and data updates, thereby placing research integrity at the heart of our platform and our development of sustainable AI. We invite publishers, researchers, and institutions to collaborate in shaping the future of AI-driven research. To learn more about partnership opportunities, visit www.zendy.io or contact us at partnerships@zendy.io. About Zendy We are an AI-powered research library with over 780,000 users across 190+ countries. Designed to streamline the research process, we provide access to millions of journals, articles, and e-books, while offering a range of AI-driven tools, including ZAIA, an AI assistant that helps researchers expedite their research journey. We collaborate with leading academic publishers to make scholarly content more accessible and affordable, ensuring that users can explore high-quality research with ease. Zendy was created to facilitate access to academic literature. By addressing the key challenges that researchers face with traditional ways of finding relevant, high-quality academic content, we strive to provide peace of mind to students, researchers, professionals, and knowledge enthusiasts. We are developed by Knowledge E in a growing collaboration with researchers, students, institutions, and publishers. Our mission is to democratise access to content by making it more affordable and accessible. There are no limitations on reading, just simple access to scholarly resources. For more information visit zendy.io. .wp-block-image img { max-width: 85% !important; margin-left: auto !important; margin-right: auto !important; }