ThoughtSpot has expanded its integration with Snowflake Cortex AI and Snowflake Semantic Views to expand how analytics agents work within Snowflake.
The changes aim to tie ThoughtSpot’s Spotter product and associated agents more closely with Snowflake’s AI and semantic tools, allowing customers to use managed business logic across both human users and software agents. It’s also designed to leverage data and definitions already managed within Snowflake’s security perimeter while keeping your analytics activities within that perimeter.
At the heart of the update is Spotter, ThoughtSpot’s analytics agent, now integrated with Cortex Analyst and Cortex Agents. Customers can access and use insights generated through Snowflake’s Cortex tools from within ThoughtSpot’s interface, rather than moving between different systems.
ThoughtSpot also adds support for native visualizations linked to Cortex-generated answers. Users will be able to transform text-based responses into interactive charts and live boards within ThoughtSpot, extending Snowflake’s AI output into more traditional business intelligence formats.
Another part of the update is a bring-your-own-model approach based on the large-scale language models hosted by Snowflake. Customers will be able to use the platform with already approved Snowflake LLMs in their environments, while keeping sensitive data within Snowflake rather than moving it to external systems.
semantic layer
The second part of the presentation will focus on data modeling and semantic management. ThoughtSpot now provides native support for Snowflake Semantic Views, allowing business logic, metrics, and relationships defined in Snowflake to flow directly into ThoughtSpot.
It also introduces bidirectional semantic management through integration with Snowflake CoCo. Customers can import semantic definitions from Snowflake into ThoughtSpot and export ThoughtSpot models back to Snowflake, including additional AI context and memory created within ThoughtSpot.
A shared semantic layer is important as many companies seek to deploy AI systems across multiple data sources without losing control of the definitions behind core metrics and business terms. In fact, mismatched definitions can lead to inconsistent output across dashboards, reports, and AI-generated answers.
The expanded integration aims to reduce that risk by making Snowflake a common source of semantic definitions while allowing ThoughtSpot’s products to operate within the same managed structure. It also covers structured and unstructured data.
agent suite
This update applies to a wide range of ThoughtSpot software agents. These include Spotter for enterprise analytics, SpotterModel for data modeling, SpotterViz for dashboard assembly, and SpotterCode for software development work linked to embedding ThoughtSpot functionality into other applications.
SpotterModel is aimed at analytical engineers and data analysts responsible for the semantic layer. Build and edit reusable data models using natural language prompts, reducing manual modeling efforts for data teams.
SpotterViz is designed to automate Liveboard creation, including layout, organization, styling, and publishing. SpotterCode, on the other hand, aims to help developers embed ThoughtSpot functions into custom applications using AI-assisted code generation in development environments such as Cursor, Claude Code, and VS Code.
These products are based on Spotter Semantics and integrated with Snowflake Semantic Views, making them more uniformly available within the Snowflake ecosystem. ThoughtSpot also supports Snowflake Interactive Analytics, which is used for highly concurrent, real-time analytics workloads.
ThoughtSpot’s platform and agent products are available through the Snowflake Marketplace, and customers can deploy them using Snowflake Credits. This route reflects a broader pattern in enterprise software. Rather than asking customers to run separate stacks, analytics and AI vendors are seeking closer commercial and technical alignment with large cloud data platforms.
François Lopiteau, ThoughtSpot’s senior vice president of product management, outlined the company’s view on how the market is changing.
“Enterprises have moved beyond seeking top-line insights from common AI agents. Winners in the enterprise AI era will be those with agent systems based on managed business context across structured and unstructured data,” said Lopitou.
“By further integrating Spotter with Snowflake Cortex AI and allowing customers to deploy their own fine-tuned Snowflake LLM, we are giving enterprises the precision, control, and data sovereignty they need to operate trusted AI at scale,” said Lopitaux.
Snowflake also framed the partnership around data governance and AI output consistency.
“The combination of Snowflake Semantic Views and ThoughtSpot’s Spotter Semantics represents a major advance in data governance and analytics. Organizations can now define semantic context for AI and BI in Snowflake and extend those definitions across the enterprise using ThoughtSpot as a trusted intelligent context layer for AI and agents. This will enable agent workflows and AI It ensures that the insights it generates are based on a single, controlled source of truth,” said Josh. Mr. Klahr is Director of Analytics Product Management at Snowflake.
