The MURE LOG #8: agents take the wheel
The data systems log, curated by humans
Hey, welcome back!
Last two weeks saw agents move from hype to infrastructure — inside banks, data platforms, and engineering workflows. This drop covers the shift from AI-assisted work to AI-orchestrated work, and what that demands from your data, tools, and team.
Our feed
01 / Design and Implementation of DuckDB Internals - Torsten Grust
Dissecting the Duck's innards, github repository here.
02 / How JP Morgan Built An AI Agent for Investment Research with LangGraph - David Odomirok & Zheng Xue
[Video] How they built "Ask David", multi-agent AI system.
03 / Agentic Data Engineering with Genie Code and Lakeflow - Gal Oshri et al.
Examples of Genie Code for pipelines.
04 / BI’s Second Unbundling - Tristan Handy
Live artifacts in Claude, create charts with AI, what should “next generation BI” look like?
05 / How to Work and Compound with AI - Eugene Yan
How can we work effectively with AI? What´s the workflow? Compounding.
06 / An open-source spec for Codex orchestration: Symphony - Alex Kotliarskyi et al.
PjM = agent orchestrator. Symphony turns a project-management board like Linear into a control plane for coding agents.
07 / AI Agent Analytics with Vercel & Motherduck - Dumky De Wilde
Vercel's Log Drains → Motherduck.
08 / On Chaos and Turning Inward - Chris Riccomini
Tiny read, good reflections.
What's new
Astronomer - introduced Otto, agent built for Airflow
AWS - MCP server now in GA
Dremio - SAP intends to acquire Dremio towards agentic lakehouse
Dremio - in preview, query Dremio Iceberg tables from Fabric
HoneyHive - introduced HoneyHive v2
OpenAI & Anthropic - launched their services arms with The Deployment Company and a new AI services company with Blackstone, Hellman & Friedman, and Goldman Sachs respectively
Outerbounds - acquired by Anaconda
SAP - to acquire Prior Labs, Tabular Foundation Models (TFM)
Simon Harrer (Entropy Data) - launched data-landscape.com, an opinionated, interactive map of the open standards
Tools & demos
Databricks - OntoBricks, tables into a materialized knowledge graph
David Cortés - pi-autoresearch, autonomous experiment loop extension for pi
Hardwood - a parser for the Apache Parquet file format, available as CLI
Microsoft - azure-skills-plugin, skills + Azure MCP + Foundry MCP
Neelesh Salian - Floe, policy-based table maintenance for Apache Iceberg
OneHouse - Quanton, a Kubernetes operator to run Spark jobs
Tobi Müller - fabric-ontology-mcp-server
Upcoming Events
AI Council · May 12 / SF
PyCon US · May 13 / Long Beach, CA
ACM CAIS (Conference on AI and Agentic Systems) · May 27 / San Jose, CA
Snowflake Summit · June 1 / SF
Microsoft Build · June 2 / SF
Databricks Data + AI Summit · June 15 / SF
EuroPython 2026 · July 13 / Kraków, Poland
DataEngBytes · July 13 / Melbourne + July 28 / Sydney
Ai4 · Aug 4 / Las Vegas
dbt Summit · Sep 15 / Las Vegas
Big Data LDN · Sep 23 / London
Microsoft Fabric Community Conference Europe · Sep 28 / Barcelona, Spain
J On the Beach · Oct 29 / Malaga, Spain
OSA CON · Nov 2 / SF
Microsoft Ignite · Nov 2 / SF
AWS re:Invent · Nov 30 / Las Vegas
Bonus: call for data speakers link
That’s all for now — we’ll be back in your inbox in two weeks.