At ThoughtSpot, we've long understood that a robust semantic layer is the linchpin of a successful data strategy. Our Agentic Analytics Platform is built on a semantic foundation that makes it possible for anyone to get trusted, instant answers from data using simple natural language.
However, the industry has struggled with a foundational challenge for years: a lack of a common semantic standard. This has left even the most powerful semantic layers isolated, with critical business context and consistent metrics trapped within individual tools.
Introducing OSI: The Open Semantic Interchange
What is OSI?
The Open Semantic Interchange (OSI) addresses this head-on. By providing a universal, open standard, the OSI will create a much-needed bridge, ensuring that the rich business context defined in our platform is seamlessly understood across the entire data ecosystem—from dashboards and notebooks to machine learning models and AI agents.
Core Principles of the OSI Framework
The OSI charter is built upon foundational principles designed to ensure its success and widespread adoption:
Standardization: We aim to establish a uniform language and structure for semantic model definitions, ensuring consistency and ease of interpretation across various tools and systems.
Interoperability: Our goal is to facilitate seamless data exchange and utilization of semantic models between diverse data analytics, AI, and BI products and services.
Extensibility: The semantic model will be designed to be adaptable and customizable, allowing organizations and vendors to extend it to meet their specific needs as data requirements, AI, and analytical use cases evolve.
Open Source: We are committed to promoting community participation and collaboration, encouraging innovation, and ensuring the framework remains relevant and effective in addressing current and future challenges in data analytics and AI/BI.
Domain-Specific Models: OSI models will simplify the process of combining and leveraging data from various sources by standardizing their semantic representation, leading to more comprehensive and accurate data analysis and data product sharing.
What the OSI Makes Possible for Agentic AI
By adopting and contributing to the OSI, we are creating a future where:
Consistency is King with a Single Source of Truth
The definitions and business logic from your semantic layer are a single source of truth, guaranteeing that every report, dashboard, and AI-generated insight speaks the same language.
This eliminates confusion and builds unprecedented trust in data, delivering productivity gains and accelerated innovation.
AI Agents Accelerate with OSI Model Layers
With a common semantic standard, AI agents—including ThoughtSpot's Spotter—can access and interpret data with a deeper, more accurate understanding of business context.
It transforms AI from a powerful but often untrustworthy tool into a trusted partner for insights, empowering every user to operate with confidence and precision.
Businesses Build with Flexibility
The OSI’s vendor-neutral approach provides our customers with the ultimate flexibility and scale to use the best tools for their specific needs, without being locked into a single ecosystem.
It promotes true semantic interoperability, allowing the data stack to work as a unified whole while enabling cost savings from reduced custom integrations.
Lead the Future of Agentic Analytics with OSI
We believe that the future of data is open and collaborative. By joining forces with Snowflake, dbt Labs, Atlan, Alation, and other industry leaders through the OSI, we are not just standardizing a technical specification; we are helping to build the foundational infrastructure for a truly fact-driven world.
The Agentic Semantic Layer and OSI: Frequently asked questions
What is the OSI model?
The OSI model is an open standard that lets tools share and understand semantic definitions, making it easier to align insights across your entire data stack.
What are OSI model layers?
OSI model layers standardize how business logic and data context are structured, enabling consistent, trusted insights across analytics tools and AI systems.
What is a semantic layer in agentic analytics?
A semantic layer defines shared metrics, terms, and business logic so teams—and AI—can work from a single, consistent source of truth.
