Cohesity Gaia Generative AI-Powered Conversational Search Assistant

Cohesity, Inc. announced Gaia, a 1st-to-market AI-powered enterprise search assistant that brings retrieval augmented generation ^(*) (RAG) AI and large language models (LLMs) to backup data within its environments.

Gaia will be made generally available on March 15. The conversational AI assistant enables users to ask questions and receive answers by accessing and analyzing their vast pools of enterprise data. When coupled with the Cohesity Data Cloud, these AI advancements transform data into knowledge and can help accelerate the goals of an organization while keeping data secure and compliant. The company has announced plans with the 3 largest public cloud providers to bring their LLM services to Gaia.

The underlying architecture of Cohesity Data Cloud manages and secures data with a blend of performance, extensibility, and scale. Gaia extends the value proposition of Data Cloud even further:

By building a RAG AI solution on Cohesity’s multicloud platform, the company will be able to y provide RAG AI conversational search experiences across cloud and hybrid environments that will allow enterprises to gain deeper insights into their data and make informed decisions in the future, no matter where their stored data resides.
The firm maintains a fully indexed backup of all files, across all workloads, and at all points in time. This robust capability supports the creation of AI-ready indexes for rapid conversational search and responses, providing enterprises with quick and accurate results. Initially, the firm will support Microsoft 365 and OneDrive data and will expand to more workloads over time.
Architecture of Gaia ensures that all indexed data is immediately available for reading without the need for backups to be reconstructed. This allows the company’s Data Cloud to function like a data lake, providing businesses with real-time access to their data for analysis and decision-making.
Data Cloud employs granular, role-based access controls and zero-trust security principles, ensuring that only authorized users and models have access to the necessary data. This not only protects sensitive information but also helps enterprises maintain compliance with various regulatory requirements.

Enterprises looking to utilize LLMs often face several challenges. Developers must first create more copies of data, thereby increasing the threat footprint for an attack. What’s more, the data may be incomplete or dated. Finally, this approach requires additional time and resources, and puts an added burden on the system’s performance. Gaia overcomes these challenges by integrating AI capabilities within a customer’s backup environment.

Gaia helps organizations make better, faster decisions across myriad of use cases, such as:

To assess an organization’s level of cyber resilience.
To quickly perform financial and compliance audit checks.
To answer complex legal questions.
To serve as a knowledge base to train new employees.

“Enterprises are excited to harness the power of generative AI but have faced several challenges gaining insights into secondary data, including backup, archived and vaulted data – because every approach requires re-hydrating the data, and painfully waiting weeks for the data to be available for analytics and insights. Gaia dramatically simplifies this process with our patent-pending approach using Retrieval Augmented Generation,” said Sanjay Poonen, CEO and president. “With Gaia, for the first time in our industry, companies will be able to leverage generative AI to query their data in a virtually seamless way. Our approach delivers rapid, insightful results without the drawbacks of more manual and risky approaches. In short, it turns data into knowledge within seconds and minutes.”

“We are an international materials research and manufacturing company, with research centers in many locations, and our researchers speak different languages,” said Ryan Reed, head, IT products and services, JSR Corporation. “We want to be able to use generative AI to quickly discover if work done at one location might apply to other projects. Gaia allows us to query our rich store of research data and quickly find relevant work. It will also allow our researchers to use their native language to query the system. This could prove incredibly valuable in accelerating the rate of our research and discovery.”

At the core of the company’s AI technologies is Cohesity Turing, a patent-pending collection of AI capabilities and technologies integrated into the firm’s multicloud data management and security platform, that provide operational and data insights. The foundation of these AI innovations is the concept of ‘responsible AI,’ with capabilities and frameworks that enable customers to introduce AI to backup data securely and safely at scale.

All Cohesity Turing solutions adhere to these responsible AI principles:

Transparency: Protect access to the data with role-based access controls. Promote transparency and accountability around access and policies.
Governance: Ensure the security and privacy of data used by AI models and the workforce – so the right data is exposed only to the right people (and models) with the right privileges.
Access: Integrate indexed and searchable data securely and easily while ensuring data is immutable and resilient.

“It is important to understand that Gaia does not retrieve data like a search engine; it answers questions,” said Greg Statton, office CTO, data and AI. ”For example, if you notice a rise in costs in a region, typically, you would search for dozens of invoices, review and compare them, and see if you can discover the reason for the cost increases. It could take hours, days, or weeks to resolve. With Gaia, you simply ask, ‘Why have costs increased in the region?’, and Gaia will pull the relevant data from your stored data, analyze it, and return an answer to your question. It’s that simple.”

“Cohesity is the first data security and management vendor to bring the power of AI search to enterprises with the Gaia AI search assistant. Gaia leverages generative AI with the latest RAG enhancements to enable conversational search across secondary protected data,” said Russ Fellows, VP, The Futurum Group Labs. “Gaia enables companies to quickly leverage their existing stored data with the power of generative AI, while preserving data security and compliance. With Gaia, customers can quickly turn data into insights, without the complexity of creating an AI application themself, or worrying about their data privacy and security.”

^(*) Retrieval augmented generation (RAG): It is a natural language processing technique that combines the benefits of retrieval-based and generative-based approaches to improve the quality of text generation tasks, such as question-answering, summarization, and conversational AI. RAG models combine the strengths of LLMs with the ability to retrieve information from multiple sources. RAG enables LLMs to generate more knowledgeable, diverse, and relevant responses and offers a more efficient approach to fine-tuning these models.

Resources:
Video: Demo of Cohesity Gaia
Blog: Scaling retrieval augmented generation systems for enterprises
Cohesity Announces Sign Up for Early Access for Cohesity Turing Integration with Amazon Bedrock – Unleashing Comprehensive Capabilities that Unlock the Power of Generative AI and Data
Cohesity Announces Partnership with Google Cloud to Help Organizations Unlock the Power of Generative AI and Data
Cohesity Unveils Key Security and Cloud Integrations with Microsoft and Announces an Expanded AI Vision