Snowflake launches Cortex Analyst, an agentic AI system for accurate data analytics

Snowflake launches Cortex Analyst, an agentic AI system for accurate data analytics Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Snowflake is all set to deploy powerful language models for complex data work. Today, the company announced it is launching Cortex Analyst, an all-new agentic AI system for self-service analytics, in public preview. First announced during the company’s data cloud summit in June, Cortex Analyst is a fully managed service that provides businesses with a conversational interface to talk to their data. All the users have to do is ask business questions in plain English and the agentic AI system handles the rest, right from converting the prompts into SQL and querying the data to running checks and providing the required answers. Microsoft Business Intelligence with SQL – YouTube Snowflake’s head of AI Baris Gultekin tells VentureBeat that the offering uses a combination of multiple large language model (LLM) agents that work in tandem to ensure insights are delivered with an accuracy of about 90%. He claims this is far better than the accuracy of existing LLM-powered text-to-SQL offerings, including that of Databricks, and can easily accelerate analytics workflows, giving business users instant access to the insights they need for making critical decisions. Simplifying analytics with Cortex Analyst Even as enterprises continue to double down on AI-powered generation and forecasting, data analytics continues to play a transformative role in business success. Organizations extract valuable insights from historical structured data – organized in the form of tables – to make decisions across domains such as marketing and sales. However, the thing is, currently, the entire ecosystem of analytics is largely driven by business intelligence (BI) dashboards that use charts, graphs and maps to visualize data and provide information. The approach works well but can also prove quite rigid at times, with users struggling to drill deeper into specific metrics and depending on often-overwhelmed analysts for follow-up insights. SQL Server Business Intelligence Features – SQL Server Data Tools “When you have a dashboard and you see something wrong, you immediately follow with three different questions to understand what’s happening. When you ask these questions, an analyst will come in, do the analysis and deliver the answer within a week or so. But, then, you may have more follow-up questions, which may keep the analytics loop open and slow down the decision-making process,” Gultekin said. To solve this gap, many started exploring the potential of large language models that have been great at unlocking insights from unstructured data (think long PDFs). The idea was to pass raw structured data schema through the models so that they could power a text-to-SQL-based conversational experience, allowing users to instantly talk to their data and ask relevant business questions. However, as these LLM-powered offerings appeared, Snowflake noted one major problem – low accuracy. According to the company’s internal benchmarks representative of real-world use cases, when using state-of-the-art models like GPT-4o directly, the accuracy of analytical insights stood at about 51%, while dedicated text-to-SQL sections, including Databricks’ Genie, led to 79% accuracy. “When you’re asking business questions, accuracy is the most important thing. Fifty-one percent accuracy is not acceptable. We were able to almost double that to about 90% by tapping a series of large language models working closely together (for Cortex Analyst),” Gultekin noted. Top SQL Business Intelligence Software in – Reviews When integrated into an enterprise application, Cortex Analyst takes in business queries in natural language and passes them through LLM agents sitting at different levels to come up with accurate, hallucination-free answers, grounded in the enterprises’ data in the Snowflake data cloud. These agents handle different tasks, right from analyzing the intent of the question and determining if it can be answered to generating and running the SQL query from it and checking the correctness of the answer before it is returned to the user. “We’ve built systems that understand if the question is something that can be answered or ambiguous and cannot be answered with accessible data. If the question is ambiguous, we ask the user to restate and provide suggestions. Only after we know the question can be answered by the large language model, we pass it ahead to a series of LLMs, agentic models that generate SQL, reason about whether that SQL is correct, fix the incorrect SQL and then run that SQL to deliver the answer,” Gultekin explains. The AI head did not share the exact specifics of the models powering Cortex Analyst but Snowflake has confirmed it is using a combination of its own Arctic model as well as those from Mistral and Meta. How exactly does it work? To ensure the LLM agents behind Cortex Analyst understand the complete schema of a user’s data structure and provide accurate, context-aware responses, the company requires customers to provide semantic descriptions of their data assets during the setup phase. This fills a major problem associated with raw schemas and enables the models to capture the intent of the question, including the user’s vocabulary and specific jargon. “In real-world applications, you have tens of thousands of tables and hundreds of thousands of columns with strange names. For example, ‘Rev 1 and Rev 2’ could be iterations of what might mean revenue. Our customers can specify these metrics and their meaning in the semantic descriptions, enabling the system to use them when providing answers,” Gultekin added. As of now, the company is providing access to Cortex Analyst as a REST API that can be integrated into any application, giving developers the flexibility to tailor how and where their business users tap the service and interact with the results. There’s also the option of using Streamlit to build dedicated apps using Cortex Analyst as the central engine. In the private preview, about 40-50 enterprises, including pharmaceutical giant Bayer, deployed Cortex Analyst to talk to their data and accelerate analytical workflows. The public preview is expected to increase this number, especially as enterprises continue to …

Read more

Snowflake launches Cortex Analyst, an agentic AI system for accurate data analytics

Snowflake launches Cortex Analyst, an agentic AI system for accurate data analytics Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Snowflake is all set to deploy powerful language models for complex data work. Today, the company announced it is launching Cortex Analyst, an all-new agentic AI system for self-service analytics, in public preview. First announced during the company’s data cloud summit in June, Cortex Analyst is a fully managed service that provides businesses with a conversational interface to talk to their data. All the users have to do is ask business questions in plain English and the agentic AI system handles the rest, right from converting the prompts into SQL and querying the data to running checks and providing the required answers. Microsoft Business Intelligence with SQL – YouTube Snowflake’s head of AI Baris Gultekin tells VentureBeat that the offering uses a combination of multiple large language model (LLM) agents that work in tandem to ensure insights are delivered with an accuracy of about 90%. He claims this is far better than the accuracy of existing LLM-powered text-to-SQL offerings, including that of Databricks, and can easily accelerate analytics workflows, giving business users instant access to the insights they need for making critical decisions. Simplifying analytics with Cortex Analyst Even as enterprises continue to double down on AI-powered generation and forecasting, data analytics continues to play a transformative role in business success. Organizations extract valuable insights from historical structured data – organized in the form of tables – to make decisions across domains such as marketing and sales. However, the thing is, currently, the entire ecosystem of analytics is largely driven by business intelligence (BI) dashboards that use charts, graphs and maps to visualize data and provide information. The approach works well but can also prove quite rigid at times, with users struggling to drill deeper into specific metrics and depending on often-overwhelmed analysts for follow-up insights. SQL Server Business Intelligence Features – SQL Server Data Tools “When you have a dashboard and you see something wrong, you immediately follow with three different questions to understand what’s happening. When you ask these questions, an analyst will come in, do the analysis and deliver the answer within a week or so. But, then, you may have more follow-up questions, which may keep the analytics loop open and slow down the decision-making process,” Gultekin said. To solve this gap, many started exploring the potential of large language models that have been great at unlocking insights from unstructured data (think long PDFs). The idea was to pass raw structured data schema through the models so that they could power a text-to-SQL-based conversational experience, allowing users to instantly talk to their data and ask relevant business questions. However, as these LLM-powered offerings appeared, Snowflake noted one major problem – low accuracy. According to the company’s internal benchmarks representative of real-world use cases, when using state-of-the-art models like GPT-4o directly, the accuracy of analytical insights stood at about 51%, while dedicated text-to-SQL sections, including Databricks’ Genie, led to 79% accuracy. “When you’re asking business questions, accuracy is the most important thing. Fifty-one percent accuracy is not acceptable. We were able to almost double that to about 90% by tapping a series of large language models working closely together (for Cortex Analyst),” Gultekin noted. Top SQL Business Intelligence Software in – Reviews When integrated into an enterprise application, Cortex Analyst takes in business queries in natural language and passes them through LLM agents sitting at different levels to come up with accurate, hallucination-free answers, grounded in the enterprises’ data in the Snowflake data cloud. These agents handle different tasks, right from analyzing the intent of the question and determining if it can be answered to generating and running the SQL query from it and checking the correctness of the answer before it is returned to the user. “We’ve built systems that understand if the question is something that can be answered or ambiguous and cannot be answered with accessible data. If the question is ambiguous, we ask the user to restate and provide suggestions. Only after we know the question can be answered by the large language model, we pass it ahead to a series of LLMs, agentic models that generate SQL, reason about whether that SQL is correct, fix the incorrect SQL and then run that SQL to deliver the answer,” Gultekin explains. The AI head did not share the exact specifics of the models powering Cortex Analyst but Snowflake has confirmed it is using a combination of its own Arctic model as well as those from Mistral and Meta. How exactly does it work? To ensure the LLM agents behind Cortex Analyst understand the complete schema of a user’s data structure and provide accurate, context-aware responses, the company requires customers to provide semantic descriptions of their data assets during the setup phase. This fills a major problem associated with raw schemas and enables the models to capture the intent of the question, including the user’s vocabulary and specific jargon. “In real-world applications, you have tens of thousands of tables and hundreds of thousands of columns with strange names. For example, ‘Rev 1 and Rev 2’ could be iterations of what might mean revenue. Our customers can specify these metrics and their meaning in the semantic descriptions, enabling the system to use them when providing answers,” Gultekin added. As of now, the company is providing access to Cortex Analyst as a REST API that can be integrated into any application, giving developers the flexibility to tailor how and where their business users tap the service and interact with the results. There’s also the option of using Streamlit to build dedicated apps using Cortex Analyst as the central engine. In the private preview, about 40-50 enterprises, including pharmaceutical giant Bayer, deployed Cortex Analyst to talk to their data and accelerate analytical workflows. The public preview is expected to increase this number, especially as enterprises continue to …

Read more

How Zebra Technologies Uses Machine Vision to Transform Production Automation

How Zebra Technologies Uses Machine Vision to Transform Production Automation Machine vision is the focus of Machine Design’s Takeover Topic Event (Aug. 12-16, 2024). Covering the gamut of vision systems, the lineup includes case histories, trends and interviews with notable players to watch in this space. In the accompanying video, Andrew Zosel, senior vice president and general manager, Zebra Technologies, explains the vision and strategy behind recent acquisitions and the resultant solutions. Machine vision is a significant part of that investment and future growth at Zebra, said Zosel. (In parts 2 and 3 of this interview series focusing on machine vision, Zosel elaborates on the following questions: Given the advancements in technology, are we still delineating between machine vision and computer vision? How are the economics of machine vision changing? What is driving the ubiquity of machine vision?) Zebra BI Cards – A unified view of your business performance in READ MORE: 10 Considerations for Designing a Machine Vision System Research commissioned by Zebra revealed that 70% of survey respondents plan to implement computer vision within the next five years. Published in June 2024, the 2024 Manufacturing Vision Study found that 86% of manufacturing leaders noted they were struggling to keep pace with technological innovation and to securely integrate devices, sensors and technologies across their facilities and supply chains. Survey respondents comprised 1,200 C-suite executives, as well as IT and OT decision-makers across various manufacturing sectors. During a stopover at Zebra Technologies’ booth at Automate 2024, Machine Design learned from Zosel just how much Zebra is leaning into building solutions that address such vulnerabilities. The variation and number of technology applications displayed revealed the pace at which Zebra has been filling in its automation ecosystem in its effort to evolve into a full-solution enterprise that can orchestrate what manufacturers on their own cannot. Expanding Zebra Technologies: Growth in Scope and Scale Zebra BI Update Top Features Bismart Partner Power BI Those familiar with Zebra Technologies likely will associate the company with its industrial printing capabilities, including scanning, track-and-trace and mobile computing and software solutions. “Our industrial are industrial printers used throughout the world,” said Andrew Zosel, senior vice president and general manager, Zebra Technologies. “The majority of the labels that go on boxes around the world, identifying and giving items a digital voice, are printed using Zebra printers because they’re extremely reliable and rugged. And that’s where the original Zebra brand came from.” In 2014, a $3.45 billion acquisition of Motorola Solutions’ Enterprise business, which included handheld scanners and mobile computers, transformed both the scope and scale of Zebra’s portfolio, then expanding further into asset visibility, traceability, barcode scanning and barcode printing capabilities. Another transformative year was 2021. Zebra acquired Fetch Robotics, Adaptive Vision and Antuit AI that year, effectively launching their machine vision and fixed industrial scanning portfolios. The acquisition of Matrox Imaging, a manufacturer of frame grabbers, vision controllers and imaging software, followed in 2022. “We’ve invested significantly, both organically with our own internal developments coming from our existing teams, in new cameras and vision and machine vision, fixed industrial scanning products, but also made a couple of significant acquisitions over the past few years in the vision space, including, Adaptive Vision out of Europe, as well as company called Matrox out of Canada.” How to Build Spectacular Microsoft Power BI Dashboards Combining Hardware and Software for Machine Vision Solutions Despite having a relatively new position in the machine and computer vision market, bringing together advancements in robotics, machine vision, automation and digital decision-making has been a surefire way to boost stealth and agility at once. “Through these acquisitions, the biggest and most important part is still the software and the algorithms and its capabilities,” said Zosel. “That’s what we’ve focused on developing and acquiring, especially the traditional machine vision capabilities such as the deterministic algorithms or however you want to call them. And a lot of development in AI and, specifically, deep learning.” Zosel pointed out that there are multiple ways to make vision systems work. The simplest method could be to use a vision sensor or a smart camera, which might comprise an all-in-one, fully integrated lens, light and computer in one product. Zebra BI Actionable Reporting Made Easy “We offer those types of products, all the way to completely disaggregated-type systems, where multiple parts come together, such as a frame grabber board in a high-end PC with a separate set of high-end cameras with separate lighting,” Zosel said. “It’s the same basic architecture of lighting, lensing, processing and compute. But it depends on the integration as well as the performance requirements of the application.” From Zebra’s perspective, said Zosel, the intent is to offer all the above. “Zosel’s platform advantage is that it has that scalability to offer everything from basic, simplified, lug-and-play-type product, all the way up to very complex, high-end systems doing either extremely high resolution or extremely high-speed processing, or both,” he said. Long-Term Strategies: Automation and Augmentation in Manufacturing Fundamentally, Zebra wants to help our customers find ways to meet the challenges they encounter, said Zosel. Microsoft-certified custom visuals for Power BI Zebra BI Packaging sustainability is a case in point. Some of Zebra’s customers are moving away from plastics by opting for thinner plastics and paper-based packaging. Zebra is helping them with inspections and helping customers along their sustainability evolution by providing products and platforms that are scalable. explained Zosel. For instance, a customer may start with 2D machine vision, but “plans for scalability to 3D and for using more advanced AI. A lot of our systems and efforts are around creating that scalability and providing that path for our customers,” Zosel explained. Zebra’s study found that over the next five years, manufacturing leaders plan to implement various automation technologies, including robotics (65%), machine vision (66%), radio frequency identification (RFID) (66%), and fixed industrial scanners (57%). The study highlighted that the adoption of these automation solutions is driven by several factors: the need to assign high-value tasks to the workforce …

Read more

How Zebra Technologies Uses Machine Vision to Transform Production Automation

How Zebra Technologies Uses Machine Vision to Transform Production Automation Machine vision is the focus of Machine Design’s Takeover Topic Event (Aug. 12-16, 2024). Covering the gamut of vision systems, the lineup includes case histories, trends and interviews with notable players to watch in this space. In the accompanying video, Andrew Zosel, senior vice president and general manager, Zebra Technologies, explains the vision and strategy behind recent acquisitions and the resultant solutions. Machine vision is a significant part of that investment and future growth at Zebra, said Zosel. (In parts 2 and 3 of this interview series focusing on machine vision, Zosel elaborates on the following questions: Given the advancements in technology, are we still delineating between machine vision and computer vision? How are the economics of machine vision changing? What is driving the ubiquity of machine vision?) Zebra BI Cards – A unified view of your business performance in READ MORE: 10 Considerations for Designing a Machine Vision System Research commissioned by Zebra revealed that 70% of survey respondents plan to implement computer vision within the next five years. Published in June 2024, the 2024 Manufacturing Vision Study found that 86% of manufacturing leaders noted they were struggling to keep pace with technological innovation and to securely integrate devices, sensors and technologies across their facilities and supply chains. Survey respondents comprised 1,200 C-suite executives, as well as IT and OT decision-makers across various manufacturing sectors. During a stopover at Zebra Technologies’ booth at Automate 2024, Machine Design learned from Zosel just how much Zebra is leaning into building solutions that address such vulnerabilities. The variation and number of technology applications displayed revealed the pace at which Zebra has been filling in its automation ecosystem in its effort to evolve into a full-solution enterprise that can orchestrate what manufacturers on their own cannot. Expanding Zebra Technologies: Growth in Scope and Scale Zebra BI Update Top Features Bismart Partner Power BI Those familiar with Zebra Technologies likely will associate the company with its industrial printing capabilities, including scanning, track-and-trace and mobile computing and software solutions. “Our industrial are industrial printers used throughout the world,” said Andrew Zosel, senior vice president and general manager, Zebra Technologies. “The majority of the labels that go on boxes around the world, identifying and giving items a digital voice, are printed using Zebra printers because they’re extremely reliable and rugged. And that’s where the original Zebra brand came from.” In 2014, a $3.45 billion acquisition of Motorola Solutions’ Enterprise business, which included handheld scanners and mobile computers, transformed both the scope and scale of Zebra’s portfolio, then expanding further into asset visibility, traceability, barcode scanning and barcode printing capabilities. Another transformative year was 2021. Zebra acquired Fetch Robotics, Adaptive Vision and Antuit AI that year, effectively launching their machine vision and fixed industrial scanning portfolios. The acquisition of Matrox Imaging, a manufacturer of frame grabbers, vision controllers and imaging software, followed in 2022. “We’ve invested significantly, both organically with our own internal developments coming from our existing teams, in new cameras and vision and machine vision, fixed industrial scanning products, but also made a couple of significant acquisitions over the past few years in the vision space, including, Adaptive Vision out of Europe, as well as company called Matrox out of Canada.” How to Build Spectacular Microsoft Power BI Dashboards Combining Hardware and Software for Machine Vision Solutions Despite having a relatively new position in the machine and computer vision market, bringing together advancements in robotics, machine vision, automation and digital decision-making has been a surefire way to boost stealth and agility at once. “Through these acquisitions, the biggest and most important part is still the software and the algorithms and its capabilities,” said Zosel. “That’s what we’ve focused on developing and acquiring, especially the traditional machine vision capabilities such as the deterministic algorithms or however you want to call them. And a lot of development in AI and, specifically, deep learning.” Zosel pointed out that there are multiple ways to make vision systems work. The simplest method could be to use a vision sensor or a smart camera, which might comprise an all-in-one, fully integrated lens, light and computer in one product. Zebra BI Actionable Reporting Made Easy “We offer those types of products, all the way to completely disaggregated-type systems, where multiple parts come together, such as a frame grabber board in a high-end PC with a separate set of high-end cameras with separate lighting,” Zosel said. “It’s the same basic architecture of lighting, lensing, processing and compute. But it depends on the integration as well as the performance requirements of the application.” From Zebra’s perspective, said Zosel, the intent is to offer all the above. “Zosel’s platform advantage is that it has that scalability to offer everything from basic, simplified, lug-and-play-type product, all the way up to very complex, high-end systems doing either extremely high resolution or extremely high-speed processing, or both,” he said. Long-Term Strategies: Automation and Augmentation in Manufacturing Fundamentally, Zebra wants to help our customers find ways to meet the challenges they encounter, said Zosel. Microsoft-certified custom visuals for Power BI Zebra BI Packaging sustainability is a case in point. Some of Zebra’s customers are moving away from plastics by opting for thinner plastics and paper-based packaging. Zebra is helping them with inspections and helping customers along their sustainability evolution by providing products and platforms that are scalable. explained Zosel. For instance, a customer may start with 2D machine vision, but “plans for scalability to 3D and for using more advanced AI. A lot of our systems and efforts are around creating that scalability and providing that path for our customers,” Zosel explained. Zebra’s study found that over the next five years, manufacturing leaders plan to implement various automation technologies, including robotics (65%), machine vision (66%), radio frequency identification (RFID) (66%), and fixed industrial scanners (57%). The study highlighted that the adoption of these automation solutions is driven by several factors: the need to assign high-value tasks to the workforce …

Read more