ARTICLES
AI Agents Must Act, Not Wait: A Case for Event-Driven Multi-Agent Design | 6 min | AI | Sean Falconer, Andrew Sellers | Personal Blog
A case for building reactive, event-driven multi-agent systems instead of static prompt chains.
Durable AI Loops: Fault Tolerance across Frameworks and without Handcuffs | AI | 10 min | Stephan Ewen, Giselle van Dongen, Igal Shilman | Restate Blog
Build long-running AI workflows that recover from failure and keep their state.
TUTORIALS
Test Driven Development (TDD) with dbt: Test First, SQL Later | 5 min | Data Engineering | Dumky de Wilde | Xebia Blog
Write tests before models and catch logic errors early.
Data pipeline troubleshooting: Root cause analysis through lineage metadata | 8 min | Data Streaming | Fiore Mario Vitale | Debezium Blog
Track root causes across CDC and streaming with Debezium and OpenLineage.
Build a Data Lakehouse with Apache Iceberg, Polaris, Trino & MinIO| 9 min | Data Engineering | Gilles Philippart | Personal Blog
Use open tools to spin up a complete, production-grade lakehouse.
Snowflake to BigQuery migration - introduction | 7 min | Data Engineering | Google Cloud Blog
Plan and execute a smooth migration from Snowflake to BigQuery with schema and SQL conversion.
TOOLS
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.
DATA TUBE
The slow death of scaling and what comes next | 1 h 2 min | ML | Sara Hooker | Cohere
Sara Hooker explores the limits of scale in machine learning and what’s coming next for open research and efficient models.
AI prompt engineering in 2025: What works and what doesn’t| 1 h 37 min | AI | Sander Schulhoff, Lenny Rachitsky | Lenny’s Podcast
Sander Schulhoff breaks down the state of prompt engineering, red teaming, and how attackers trick LLMs through advanced injection techniques.
PINNACLE PICKS
Your last week top picks:
Embedding User-Defined Indexes in Apache Parquet Files| 7 min | Data Engineering | Qi Zhu, Jigao Luo, Andrew Lamb | Apache DataFusion Blog
DataFusion introduces custom Parquet indexing for faster queries on large datasets.
NVIDIA Says Small Language Models Are The Future of Agentic AI | SLM | 5 min | Cobus Greyling | Personal Blog
Small models are faster, safer, and better suited for real-time AI. NVIDIA explains why they may outpace large LLMs in practical applications.
The Agent Factory - Episode 2: Multi-Agent Systems, Concepts & Patterns | 23 min | Gen AI | Vlad Kolesnikov, Shir Meir Lador | Google Cloud Tech
Vlad Kolesnikov and Shir Meir Lador explain how to design collaborative agents using swarms, supervisors, and context engineering.
________________________
Have any interesting content to share in the DATA Pill newsletter?
