Snowflake introduces Cortex Agents for managing enterprise data

While AI agents promise to boost business productivity by automating complex tasks, their effectiveness hinges on access to high-quality structured and unstructured data. However, managing access control and maintaining strict privacy protocols while efficiently retrieving accurate information presents a significant challenge for many organisations.

To address this problem, Snowflake is launching Cortex Agents, a fully managed service that simplifies integration, retrieval and processing of structured and unstructured data — helping customers build high-quality agents at scale.

Mohamed Zouari, General Manager, META at Snowflake: “For AI to deliver real value, enterprises need a robust, governed, and scalable approach to managing structured and unstructured data. With AI expected to contribute up to USD 320 billion to the MENA economy by 2030, the region’s rapid adoption of AI-driven solutions demands accurate, secure and intelligent data management. With Cortex Agents, Snowflake empowers businesses to build high-quality AI agents that drive automation, analytical insights, and company growth. By streamlining data retrieval and processing, enterprises can fully capitalize on AI’s potential while maintaining compliance and being business-ready for the Middle East’s evolving digital economy.”

Cortex Agents: Bringing AI to enterprises

Cortex Agents, now available in public preview, orchestrates structured and unstructured data sources — whether Snowflake tables or PDF files stored in object storage — to deliver insights. They break down complex queries, retrieve relevant data and generate precise answers, using Cortex Search, Cortex Analyst and LLMs. This enables accuracy, efficiency and governance at every step. Cortex Agents plan tasks, use tools to execute them, and reflect on results to improve responses. Available as a convenient REST API, Cortex Agents can seamlessly integrate into any application.

Cortex Analyst: AI-powered SQL generation, with semantic understanding

Cortex Analyst can be used as a tool within Cortex Agents. Unlike typical text-to-SQL systems that rely only on pattern matching, Cortex Analyst uses a semantic model to map business terms to underlying data. This unique approach improves precision in real-world use cases that involve complex multi-table environments.

1. Handling increased schema complexity: Our new advanced JOIN validation mitigates common issues, such as JOIN hallucinations and double counting, which often arise in complex queries. This allows Cortex Analyst to support multi-table queries without compromising precision.

2. Semantic model generation and monitoring: Our public preview of the new Analyst Admin UI in Snowsight simplifies the process of building and refining semantic models. Admins can select tables and columns, and use LLMs (running within Snowflake’s secure perimeter) to generate a starting Semantic Model YAML file. The admin interface also monitors user engagement and feedback. This allows customers to track usage, and make informed improvements to semantic models over time.

3. Customization for business-specific logic: With Custom Instructions now in GA, users can tailor Cortex Analyst to their unique business needs using natural language in the Semantic Model file. Common use cases include specifying fiscal year start dates, explaining internal naming conventions and prioritizing key tables during SQL generation.

Cortex Search: High-quality context engine for unstructured data

Cortex Agents use Cortex Search to retrieve unstructured data (e.g., text, audio, image, video). Cortex Search is a natively hybrid search, a combination of vector and lexical (keyword) search, with an additional semantic reranking step, to deliver high-quality, low-latency retrieval at scale.

Cortex Search achieves state-of-the-art quality, outperforming competing enterprise search stacks on retrieval accuracy (NDCG@10) with OpenAI embedding models by at least 11% across a diverse set of benchmarks.

1. Increased scale and affordability: Cortex Search now supports indexing hundreds of millions of rows. Additionally, serving costs for Cortex Search have been reduced by 30% as a result of infrastructure optimizations.
   
   
2. Improved customizability: Cortex Search now provides the ability to select the vector embedding model for semantic search. This includes two multilingual models, snowflake-arctic-embed-l-v2.0 and voyage-multilingual-2. Additionally, Cortex Search supports date-range filtering on metadata columns.

3. New preview features: New preview features include the Cortex Search Admin UI (for observability and quality tuning); boosting and decays on numeric and time signals; result confidence scores; and advanced filtering capabilities.

AI Observability: Evaluation and tracing of AI Agents

AI observability brings reliability, performance and trust to generative AI applications. With proper evaluations and monitoring, businesses can get more accurate results, optimize costs and address their governance needs.

Cortex AI Observability on Snowflake is powered by TruLens and will be available in public preview soon.

1. End-to-end evaluation: AI Observability can evaluate the performance of agents and apps, using techniques such as LLM-as-a-judge. It can report metrics such as relevance, groundedness and harmfulness, giving customers the ability to quickly iterate and refine the agent for improved performance.
   
   
2. Comparison: Users can compare evaluation runs side-by-side and assess the quality and accuracy of responses across different LLM configurations to identify the best configuration for production deployments.
   
   
3. Comprehensive tracing: Customers can enable logging for every step of agent executions across input prompts, tool use and final response generation. This allows easy debugging and refinement for accuracy, latency and cost.

Effective governance and processing of both structured and unstructured data within Snowflake are crucial for creating AI-ready datasets that retrieval services can utilize. Snowflake’s support for unstructured data includes capabilities to store, access, process, manage, govern and share such data. The Snowflake Connector for SharePoint checks that existing permissions are respected to secure access controls. Furthermore, Snowflake’s acquisition of Datavolo enhances the platform’s ability to handle multimodal data integration, reinforcing its commitment to robust data governance and processing.

With these capabilities, Cortex AI Observability makes AI applications more efficient and trusted for enterprise use.

The future of AI agents

AI agents are moving beyond basic automation, dynamically handling multi-step actions and reasoning. This is a significant improvement over the mostly reactive software tools available today. As LLMs continue to advance, agents will collaborate, plan, execute, and refine tasks, driving efficiency and reducing costs. Agents have the potential to reduce both software and labor expenses by orders of magnitude.

Cortex Agents, using Cortex Analyst, Cortex Search, and AI Observability, bring intelligence on top of a unified governance framework and efficient processing engine for both structured and unstructured data.

Last Updated on 6 hours by News Desk 1