Arctic Agentic RAG — Snowflake’s next-gen AI framework for enterprise retrieval-augmented generation, delivering smarter, faster, and more reliable AI insights.
FEB 18, 2025|5 min read
Engineering Blog
Hear directly from Snowflake’s technical leaders about what we build, why and how we build it, and how you can use it.
HOT OFF THE PRESS
MAR 13, 2025|14 min read
MAR 11, 2025|15 min read
LATESTPOSTS
OUR CATEGORIES
Snowflake Cortex Analyst: Preventing Join Hallucinations and Double Counting
Snowflake Cortex Analyst introduces a new ability to support complex schemas, expanded our join capabilities beyond simple star and snowflake schemas to support multifact tables and measures spread across multiple tables.
FEB 20, 2025|15 min read
Profiling Python Stored Procedures to Identify Inefficiencies
Optimize Snowpark Python stored procedures with the new built-in profiler, helping users identify inefficiencies, track execution time, and enhance performance.
FEB 19, 2025|5 min read
Arctic Agentic RAG Episode 1: Agentic Query Clarification for Grounded and Speedy Responses
Discover how Arctic Agentic RAG improves AI accuracy with agentic query clarification, delivering grounded, speedy responses for enterprise AI applications.
FEB 18, 2025|9 min read
Introducing Arctic Agentic RAG: Smarter, Faster and More Reliable AI for Enterprise
Arctic Agentic RAG — Snowflake’s next-gen AI framework for enterprise retrieval-augmented generation, delivering smarter, faster, and more reliable AI insights.
FEB 18, 2025|5 min read
Snowflake’s Cortex Search: Unmatched Search Quality and Simplicity for All Your Search Needs
Unlock insights from unstructured data with Snowflake Cortex Search — delivering unmatched search quality, easy SQL-based deployment and AI-powered retrieval.
FEB 13, 2025|21 min read
Eval-Guided Optimization of LLM Judges for the RAG Triad
Learn how eval-guided optimization enhances LLM Judges for RAG systems, improving context relevance, and answer relevance with advanced benchmarking.
FEB 04, 2025|8 min read
Benchmarking LLM-as-a-Judge for the RAG Triad Metrics
Evaluating RAG systems with LLM-as-a-Judge: explore our benchmarking results and learn how the RAG Triad metrics build trust in enterprise RAG systems.
JAN 31, 2025|22 min read
Creating Automated Optimizations for Python User-Defined Functions with Snowpark's Parallel Execution
Snowpark’s parallel execution optimizes Python UDF performance, addressing Python global interpreter lock and data skew with advanced redistribution techniques.
JAN 30, 2025|4 min read
Machine Learning Models Require the Right Explanation Framework — and It’s Easy to Get Wrong
Learn the importance of using a robust explanation framework for machine learning models, ensuring accuracy, trust and understanding for better decision-making.
JAN 23, 2025|7 min read