A case for building reactive, event-driven multi-agent systems instead of static prompt chains.
Build long-running AI workflows that recover from failure and keep their state.
Write tests before models and catch logic errors early.
Track root causes across CDC and streaming with Debezium and OpenLineage.
Use open tools to spin up a complete, production-grade lakehouse.
Plan and execute a smooth migration from Snowflake to BigQuery with schema and SQL conversion.
Build fault-tolerant, long-running AI agents directly on Flink using native state and streaming.
Store and retrieve vector embeddings natively in S3 to simplify RAG and GenAI pipelines.
Sara Hooker explores the limits of scale in machine learning and what’s coming next for open research and efficient models.
Sander Schulhoff breaks down the state of prompt engineering, red teaming, and how attackers trick LLMs through advanced injection techniques.
DataFusion introduces custom Parquet indexing for faster queries on large datasets.
Small models are faster, safer, and better suited for real-time AI. NVIDIA explains why they may outpace large LLMs in practical applications.
Vlad Kolesnikov and Shir Meir Lador explain how to design collaborative agents using swarms, supervisors, and context engineering.