We want to hear from you. Take our short AI survey and let us know your thoughts about the current state of AI, how you’re implementing it, and your hopes for the future. learn more
Writeris an AI platform for major companies. Powerful enhancements Significant improvements to the company’s artificial intelligence chat application announced today at VB Transform include advanced graph-based search extension generation (Rugs) and new AI transparency tools are rolling out across the Writer ecosystem starting tomorrow.
Writer’s pre-made “Ask the writer” Applications and developers AI Studio Users of our platform for building custom solutions will have immediate access to these new capabilities, and this broad rollout marks a major step forward in making advanced AI technologies more accessible and effective for businesses of all sizes.
At the heart of the upgrade is a dramatic expansion of data processing power. The improved chat app will Analyze up to 10 million words It aggregates enterprise-specific information, enabling organizations to leverage their own data at an unprecedented scale when interacting with AI systems.
Unleashing the power of 10 million words: How Writer’s RAG technology is transforming enterprise data analytics
“We know that companies need to analyze very long files or deal with long research papers or documents, and that’s a big use case for them,” Deanna Dong, product marketing lead at Writer, told VentureBeat in an interview. “We’re actually using RAG to do knowledge search.” [large language model] If you are doing an LLM of the entire library, you just do the actual research, pull out all the appropriate notes, and provide the appropriate resource notes for the LLM.”
Countdown to VB Transform 2024
Join enterprise leaders at our flagship AI event in San Francisco July 9-11. Network with your peers, explore the opportunities and challenges of generative AI, and learn how to integrate AI applications in your industry. Register now
The key innovation is the lighter A graph-based approach to RAGmaps semantic relationships between data points rather than relying on simpler vector searches, which Dong says enables more intelligent and targeted information retrieval.
“We break down the data into little data points and then we actually map the semantic relationships between those data points,” she says. “So a snippet about security is linked to this tidbit of information about the architecture, and this is actually mapping the data in a more relational way.”
A peek into the mind of AI: Writer’s “Thought Process” feature brings unprecedented transparency into AI decision-making
this Graph-based RAG system new”Thought ProcessThe ability to “provide unprecedented transparency into the process the AI takes to arrive at a response.” The system shows users the steps the AI takes, including how it breaks down a query into sub-questions and the specific data sources it references.
“We’re showing you the steps that the AI is taking,” Dong explained, “taking what may be a broad question that you’re asking, or a question that’s not very specific, and actually breaking it down into the sub-questions that the AI assumes you’re asking.”
Writer CEO May Habib emphasized the importance of these advancements in a recent interview with VentureBeat. “RAGs aren’t easy,” she said. “When you talk to CIOs and VPs of AI and people who are trying to build their own RAGs and care about accuracy, they tell you it’s not easy. And when it comes to benchmarking, a recent benchmark of eight different RAG approaches, including the Writer Knowledge Graph, found that: We came first accurately.”
Customized AI Experience: New Writer “Modes” Streamline AI Deployment in the Enterprise
The upgrade also introduces dedicated “modes” – interfaces specialized for different types of tasks, such as general knowledge queries, document analysis, and knowledge graph manipulation, aimed at simplifying the user experience and improving the quality of the output by providing more tailored prompts and workflows.
“We saw customers struggling to use a generic chat interface to complete any task,” Dong explains. “They couldn’t prompt accurately, they didn’t get the right results, and they would forget to say, ‘I’m looking at this file,’ or ‘I need to use our internal data for this answer.’ And it was confusing for customers.”
Industry analysts believe that Writer’s innovations have the potential to revolutionize enterprise AI adoption: The combination of large-scale data ingestion, sophisticated RAGs, and explainable AI removes several key obstacles that hold many enterprises back from broadly adopting LLM-based tools.
The new capabilities will be automatically available in Writer’s pre-built “Ask Writer” chat application as well as custom chat apps built on the Writer platform. This broad availability has the potential to accelerate AI integration across various enterprise functions.
“All of these features — the modes, the thought process, the ability to incorporate RAGs — make this whole package of very sophisticated technology very easy to use for the end user,” Dong says. “The CIO will be amazed at the built-in RAGs, but the end user — the operations team, the HR team — doesn’t need to understand any of this. What the end user really gets is accuracy, transparency and ease of use.”
As businesses explore how to leverage AI responsibly and effectively, Writer’s latest innovation offers a compelling vision of more transparent, accurate, and user-friendly LLM applications. The coming months will reveal whether this approach can bridge the gap between AI’s immense potential and the practical reality of enterprise deployment.