Regional Director

ThoughtSpot has launched Spotter Semantics, an agentic semantic layer designed to deliver consistent and trustworthy analytics for enterprise AI. The platform transforms fragmented data into governed business context that AI agents can understand and act upon. Built on ThoughtSpot's AI-native foundation, Spotter Semantics uses a patented search-token architecture and ThoughtSpot Modeling Language to ensure natural language queries produce accurate, explainable answers at scale. Unlike legacy BI tools retrofitting AI capabilities, ThoughtSpot's semantic layer was designed from inception to support natural language search. The company emphasises its deterministic approach relies on search tokens rather than LLM-powered text-to-SQL, enabling consistent insights regardless of how questions are posed. Spotter Semantics serves as a context-aware translation engine between complex data sources and AI agents, addressing the challenge of ensuring uniform analytics quality across different users and agents.

ThoughtSpot aims to simplify analytics: smarter BI tools. ThoughtSpot unveils a unified platform of AI BI agents, including Spotter 3, to automate analytics workflows and help teams turn raw data into insights faster. AI is having its big moment, but actually making sense of data is still a very real, very necessary part of the job. ThoughtSpot is rolling out a whole crew of AI-powered BI agents, all designed to work together instead of living in their own little silos. The lineup includes SpotterViz, SpotterModel, SpotterCode and the upgraded Spotter 3. Each one is designed to deal with a different part of the workflow, helping teams get real insights from raw data without spending half their day on the repetitive tasks. A unified platform for agentic AI comes to business intelligence. "... we are delivering the industry's first unified platform that augments every role analysts, data engineers, developers, and business users with an intelligent agent that handles the manual work," said Francois Lopitaux, SVP of product management. "It is the foundational element towards the autonomous enterprise, turning intelligence into an engine that continuously drives business forward and delivers ROI on your AI investments." The idea here is pretty simple. Let AI handle the tedious parts so people can stay focused on the kind of thinking that actually matters. How each agent helps different teams work faster. SpotterViz for analysts. SpotterViz focuses on dashboard creation. Analysts describe what they need in natural language and SpotterViz handles the layout, styling, organization and publishing. This helps analysts spend less time arranging charts and more time understanding what the data is actually saying. SpotterModel for data engineers. SpotterModel helps engineers build models faster by using simple natural-language prompts to create governed, reusable semantic models. It can recommend the right tables, joins, and logic based on business rules, and it works across Snowflake, Databricks, and dbt. Lopitaux highlighted that these agents still keep people in control, saying, "There is a strong component of human in the loop. SpotterModel comes back with a suggestion, but the human needs to validate it." SpotterCode for developers. SpotterCode acts like an AI pair programmer inside tools such as Cursor, Claude Code, GitHub Copilot, and VSCode. It understands the context of a developer's project and generates high-quality code for embedding ThoughtSpot capabilities. This helps developers build intelligent, branded experiences inside their applications. Spotter 3 ties the whole ecosystem together. Spotter 3 is the updated intelligence engine that corrals everything into one place. It combines structured and unstructured data, connects with tools such as Slack and Salesforce, generates Python when needed, and evaluates the quality of its own answers before returning a result. This gives users more confidence in the outcomes and reduces the back-and-forth that can come with complex questions. Shiva Somasundaram, senior director of product at Tekion, noted the practical impact. "The new suite of agents looks promising," he said. "We are looking forward to putting them to use. We anticipate this will drastically reduce the time our analysts spend on manual tasks, allowing them to shift their focus entirely to high-value strategic interpretation." John Santaferraro, CEO of Ferraro Consulting, added, "The end goal of analytics is to get more people using insights to make decisions. ThoughtSpot's two-pronged approach simultaneously empowers non-technical business users with accessible insight and dramatically boosts the productivity of data engineers and analysts." Spotter 3 is available now to select customers, with the remaining agents rolling out over the next few months. Dell's latest enhancements to the Dell AI Data Platform also center on clearing out data bottlenecks and making AI workloads easier to run across distributed environments. Taken together, both updates show the strong demand for technologies that streamline the messy middle between data and insight. Allison is a contributing writer for Channel Insider, specializing in news for IT service providers. She has crafted diverse marketing, public relations, and online content for top B2B and B2C organizations through various roles. Allison has extensive experience with small to midsized B2B and channel companies, focusing on brand-building, content and education strategy, and community engagement. With over a decade in the industry, she brings deep insights and expertise to her work. In her personal life, Allison enjoys hiking, photography, and traveling to the far-flung places of the world. CrewAI's CEO explains why human oversight, guardrails, and accountable systems are key to safe, scalable adoption. Microsoft redefines AI at Ignite 2025, unveiling an end-to-end ecosystem that reshapes how organizations build, deploy and securely govern AI agents. Sage launches its Finance Intelligence Agent, a new AI tool in Sage Intacct that delivers real-time insights, automates finance workflows, and accelerates decisions. Frontegg launches AgentLink, an enterprise-grade MCP server enabling SaaS apps to securely connect APIs to AI agents like ChatGPT, Claude, and Gemini.

ThoughtSpot aims agents at the analytics lifecycle. ThoughtSpot Inc. today introduced a suite of business intelligence agents designed to automate major components of the analytics workflow, spanning data modeling, dashboard creation, embedded development and real-time analytical queries. The four agents - SpotterModel, SpotterViz, SpotterCode and an upgraded Spotter 3 - extend the company's push into what it calls "agentic analytics," a model that uses semi-autonomous software agents to reduce manual work for data engineers and business users. "Our customers spend a lot of time building pipelines, semantic models and dashboards but not really providing insight," said Francois Lopitaux, senior vice president of product management at ThoughtSpot. The new agents are designed to pair with different personas involved in analytics operations, such as analysts and developers. "We want to provide a friend in the business that helps them to perform their tasks better," Lopitaux said. Embedded development. ThoughtSpot said SpotterModel simplifies semantic modeling by proposing tables, joins and logic based on natural-language instructions. Though agents are capable of full autonomy, their primary role is as advisers, Lopitaux said. "There is a strong component of human in the loop," he said. "SpotterModel comes back with a suggestion but the human needs to validate it." SpotterViz (pictured) automates dashboard creation, including layout, design and the selection of key performance indicators. While ThoughtSpot executives have been vocal in advocating for users to move beyond dashboards, "people are still using them and we want to make it easy for them to transition to the next generation," Lopitaux said. For developers, SpotterCode provides code generation and embedded analytics support within popular integrated development environments. The agent understands each developer's project context and can generate code ThoughtSpot code derived from the company's software development kit. "It's like having an expert sitting next to you," Lopitaux said. "When you need it, you can tap into its knowledge or even ask it to write the code." At the center of everything is Spotter 3, the newest version of ThoughtSpot's agentic analyst. Spotter allows users to ask analytical questions and get answers without building dashboards or using structured query languages. Lopitaux said the new version system can answer complex queries, integrate with third-party software using the Model Context Protocol and generate Python code when needed. "You can plug Spotter 3 directly into a company's SaaS applications," he said. "Spotter is able to not only use the data that is available to ThoughtSpot, but also reach out to bring additional information." To guard against errors and hallucinations, Spotter 3 applies iterative reasoning to evaluate and refine its own results. "Every time you ask a question, it explains its chain of thought," Lopitaux said. ThoughtSpot also uses its own search-token technology to generate SQL rather than relying on large language models. The agents don't yet coordinate autonomously with each other, though they operate on a shared metadata layer. Lopitaux said cross-agent cooperation is on the company's roadmap. The company is also developing customizable agents that can perform specialized tasks, such as identifying customers likely to churn. Spotter 3 and the new agents are scheduled for release early next year. Image: ThoughtSpot. A message from John Furrier, co-founder of SiliconANGLE: Support its mission to keep content open and free by engaging with theCUBE community. Join theCUBE's Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities. * 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more * 11.4k+ theCUBE alumni - Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network. SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios - with flagship locations in Silicon Valley and the New York Stock Exchange - SiliconANGLE Media operates at the intersection of media, technology and AI. Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Its new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.