Yu Ishikawa·Sep 19Calling Typed AI from SQL: Jev, dbt, and DuckDBCalling Typed AI from SQL: Jev, dbt, and DuckDB
Yu Ishikawa·Aug 28Lightdash at Ubie Part 7:AgentOps as Code — Building Reliable AI Analytics Agents with Coding…AgentOps as Code: coding agents iterate on versioned agent state and validate behavior through repeatable evaluations.
Yu Ishikawa·Aug 17From MCP Prototype to Enterprise Platform: Seven Design Patterns for Internal MCP ServersAbout a 10-minute read for staff engineers, architects, AI platform engineers, and security-minded developers.A response icon1A response icon1
Yu Ishikawa·Aug 15Lightdash at Ubie Part 6: Building Secure, Purpose-Built Analytics Applications with Lightdash…In Part 5, I wrote about the official Lightdash MCP and how it lets coding agents work directly with our governed analytics layer.
Yu Ishikawa·Aug 15Lightdash at Ubie Part 5: From BI to Agentic BI with the Official Lightdash MCPIn the previous article, I wrote about how Lightdash AI Agents can make business intelligence more conversational. This time, I want to…
Yu Ishikawa·May 1AI Agents Need a Harness for Complexity of dbt ModelsHow a custom SQLFluff plugin can give coding agents feedback before complex SQL reaches human review.
Yu Ishikawa·Jan 31Don’t Just Prompt, Orchestrate: The Architecture of Multi-Agent Team ManagementMoving beyond “chatting with code” to managing autonomous sub-agent swarms.
Yu Ishikawa·Jan 26The Agentic Makefile: Why Every Repository Needs a Self-Describing AI LayerIf you’ve started using AI agents like Claude Code or Cursor lately, you’ve likely encountered a new kind of friction.
Yu Ishikawa·Jan 22Beyond the Data Mesh: The Shift to Human-to-AI-to-Human Enablement in Data Platform EngineeringFor the last few years, Data Platform Engineering has been chasing the dream of “Self-Service Analytics” and the “Data Mesh.” We built…