ThoughtSpot Expands Governed Enterprise AI with Snowflake Cortex AI and Semantic Views

New integrations with Snowflake Semantic Views and Cortex AI allows teams to define, manage, and scale governed business logic across human and agent workflows

ThoughtSpot, the Agentic Analytics Platform company, announced at Snowflake’s annual user conference, Snowflake Summit 26, integrations of Spotter and its suite of agents with Snowflake Cortex AI and Snowflake Semantic Views. This technical optimization provides Snowflake customers with a unified analytics experience, allowing high-reasoning agents to operate directly within the Snowflake security boundary while maintaining a single, governed source of truth.

As enterprises increasingly adopt sophisticated agentic workflows, ensuring these are powered by high-reasoning, consistent intelligence reflective of strong semantic boundaries is critical. The deepening of ThoughtSpot’s integration with Snowflake Cortex AI means businesses can be assured that the intelligence powering business decisions is governed, secured and scalable. By combining ThoughtSpot’s intuitive interface with Snowflake-hosted LLMs, organizations can finally move past data silos to a model where trusted insights are generated directly where the data lives.

Also Read: AiThority Interview with Matej Bukovinski, Chief Technology Officer at Nutrient

Key capabilities of the expanded integration include:

• Spotter + Cortex Integration: ThoughtSpot’s core intelligence engine, Spotter, will now integrate directly with Cortex Analyst and Cortex Agents. Customers can now access, action and workflow Cortex insights directly within Spotter – ensuring teams have access to a consistent and holistic view of all company information, no matter where the data sits.
• Cortex-Powered Visualizations: While users can currently leverage Cortex AI for deep, text-based insights, ThoughtSpot will continue bringing increased business intelligence to Cortex AI with the launch of native visualization support. This upcoming feature will allow answers generated by Cortex to be instantly transformed into fully interactive charts and Liveboards, closing the loop between raw AI reasoning and visual storytelling.
• Bring Your Own Snowflake LLM: This “Bring Your Own LLM” approach gives customers ultimate control over their AI architecture. It allows businesses to utilize ThoughtSpot within the specific Snowflake LLMs already vetted and optimized for their unique business vocabulary, while simultaneously supporting a strong data sovereignty footprint by ensuring sensitive data never leaves the Snowflake security boundary. Meaning all data remains under the direct stewardship of the enterprise data team.

Governed Semantic Flexibility: Native Support & Bi-Directional Management

ThoughtSpot is also helping customers remove the friction of manual data modeling by providing native, deep-rooted support for Snowflake Semantic Views. This integration ensures the business logic, metrics, and relationships defined within Snowflake flow into ThoughtSpot seamlessly.

• A critical element of semantic flexibility, ThoughtSpot is now providing customers with bi-directional semantic management through an integration with Snowflake CoCo. This allows customers to not only import semantics from Snowflake into ThoughtSpot, but also export ThoughtSpot Models enriched with advanced AI context and memory back into Snowflake, ensuring a single, governed source of truth for both human users and agents.

All Through a Custom Built, Unified Team of Agents

Grounded in Spotter Semantics and natively integrated with Snowflake Semantic Views, customers can now a enjoy a unified agentic experience across ThoughtSpot’s suite of intelligent agents – Spotter, SpotterModel, SpotterViz, and SpotterCode – without needing to leave the Snowflake ecosystem.

• Spotter: ThoughtSpot’s enterprise analytics agent, enabling users to ask questions, investigate drivers, and act on governed enterprise data across structured and unstructured sources.
• SpotterModel: Built for the analytics engineers or data analysts managing the semantic layer, SpotterModel automates the foundational work of data modelling, allowing data teams to simply use natural language prompts to build and edit governed, reusable semantic models.
• SpotterViz: SpotterViz brings autonomy to the “last mile” of data storytelling by automating the time-consuming assembly of Liveboards—handling layout, organization, styling, and publishing—through natural language prompts.
• SpotterCode: The developer agent that assists developers in embedding ThoughtSpot’s intelligence into custom applications with AI-assisted code generation in popular IDEs, like Cursor, Claude Code, and VS Code.

To ensure the continued effectiveness of a company’s “last mile” of data interaction, ThoughtSpot also natively supports Snowflake Interactive Analytics. This means customers can continue optimizing the costs of serving high-concurrency, real-time analytics–including modern streaming workloads–at enterprise scale. ThoughtSpot provides the intuitive, interactive UI and visualization layer on your Snowflake data that makes low-latency analytics accessible to every user.

“Businesses have moved beyond wanting top line insights driven by general AI agents. The winners in the enterprise AI era will be the organizations whose agentic systems are grounded in governed business context across structured and unstructured data,” said Francois Lopitaux, SVP of Product Management at ThoughtSpot. “By further integrating Spotter with Snowflake Cortex AI and allowing customers to bring their own fine-tuned Snowflake LLMs, we are giving enterprises the accuracy, control, and data sovereignty they need to operationalize trusted AI at scale.”

“The combination of Snowflake Semantic Views and ThoughtSpot’s Spotter Semantics represents a massive leap forward for data governance and analytics. Organizations can now define their semantic context for AI and BI once in Snowflake and use ThoughtSpot as a trusted intelligent context layer for AI and agents to scale those definitions across the enterprise. This helps ensure that agentic workflows and AI-generated insights are based on a single, governed source of truth,” said Josh Klahr, Director of Product Management, Analytics at Snowflake.

Also Read: ​​AI systems – Interoperable AI systems: Connecting models across platforms

[To share your insights with us, please write to psen@itechseries.com]