Scaling Agent Context with Knowledge Graphs on Snowflake
How knowledge graphs extend the working context available to AI agents beyond fixed dashboards and flat retrieval, implemented on Snowflake.
Data Platform Architect & Analytics Product Builder
Data platform architect and analytics product builder known for deep work benchmarking Databricks and Snowflake compute and delivering high-performance data applications at scale. Builds full-stack analytics solutions — from billion-point time-series engines to portfolio optimization apps and real-time financial dashboards — blending Databricks, Snowflake, Rust, Arrow, and modern web technologies.
How knowledge graphs extend the working context available to AI agents beyond fixed dashboards and flat retrieval, implemented on Snowflake.
A data-driven analysis running the full TPC-DS suite (4,750+ queries) across three Databricks compute planes via Apache JMeter; serverless SQL warehouses (DBSQL) emerge as the overall winner — roughly 7x faster than any Jobs compute at equal or lower cost — while classic Jobs Compute wins within the Jobs family.
Turning Databricks System Tables into a knowledge base for an AI agent answering GenAI cost questions; makes the case for Unity Catalog functions over text-to-SQL to eliminate injection surface.
Hands-on evaluation of Snowflake's Cortex Code CLI across five test areas spanning 55 billion rows.
At-scale interactive Dash apps over large IoT time-series via the Databricks SQL connector, Plotly Resampler downsampling, Polars backend.
Dash as a front end for the Databricks SDK and Jobs API.
Connecting Dash to Databricks via the SQL connector or SQLAlchemy ORM; streaming dashboards, DDL/object mapping, advanced visuals.
Production customer data app using the SQLAlchemy engine and Dash AG Grid.
Full-stack Dash app that deploys Hugging Face / Databricks models to GPU serving endpoints.