Norman

@rauchg Not entirely built with AI but helped a lot getting way faster with Rust. strakedata.com Gemini + Antigravity

Show me the thing you’ve built with AI you’re most proud of. Reply with a working product URL and what model / agent you primarily used.

@KostasPardalis @andrewlamb1111 @ApacheDataFusio hopefully not too shameless self marketing, but my (side) project tries to hit this area. High performance data federation in Datafusion, sandboxed environments and MCP code mode as a unified, governed data access for agents. github.com/strake-data/st…

@andrewlamb1111 @ApacheDataFusio @LangChain this is amazing @andrewlamb1111 is there a list of all the AI related projects that use DataFusion? It seems that agents are in need of foundations coming from systems like DataFusion, it's important for people to realize that.

A new Database product based on @ApacheDataFusio was announced today from @LangChain -- focused on agent observability. It is really neat to see how people are building (very) customized data + query systems faster than ever now that they don't have to build the whole stack

@HoytEmerson yes! No doubt about that and I am a huge fan of duckdb for pushing and improving things.

@norm227 In the latest Iceberg summit they hinted at handling this in upcoming versions of Iceberg. But DuckLake’s approach is really elegant.

DuckLake v1.0 has a feature called "inlining". This allows you to stream directly to DuckLake without creating a file for each INSERT. The row data is stored in the metadata database first and referenced when queried. You then use CHECKPOINT to flush the data to a Parquet file.

@jrdntgn Hi Jordan, Just read your "future casting" article and thought it was a very interesting read! I wondered about the yaml is replaced by natural language take. Don't you think it's a decent token dense representation that could be still be beneficial for definitions?

@RhysSullivan very interesting! I think the execution layer also generalizes for SQL. Compute in a sandboxed environment with a unified interface for various sources seems to me like the way to go for enterprise use cases.

The first blog post on how we see Strake as a solution for token efficient and safe way of using AI agents in production #ai #mcp open.substack.com/pub/strakedata…

@denodo Or see this gif

VQLForge now has an #AIAgents mode for autonomous, end-to-end #SQL to VQL migration. It handles the entire workflow, from translation to validation, completely hands-free. Link: github.com/banickn/VQLFor… #AI #Data @Denodo #OSS #Snowflake #DataMigration github.com/banickn/VQLFor…

Excited to share my open-source project: VQLForge! It translates 24 SQL dialects to Denodo #VQL + featuring an AI agent for error analysis & validation. Accelerate your @Denodo migrations! github.com/banickn/VQLFor…… #Denodo #SQL #OpenSource #AI #DataMigration #DataMangement

2 years ago I started to train with @TrainerRoad Last sunday I won overall #Ironman Vichy with the best bikesplit. Thanks a lot, guys. You are the best 😎👍 #ironmanvichy2018