Artificial Intelligence

Shannon Smith

Move Fast and Don’t Break Things: Shipping the Simplenote MCP

When Automattic recently launched a month‑long hackathon, engineers Mark Biek and Evan Tobiesen knew exactly what they wanted to work on: the Simplenote Model Context Protocol (MCP) server. Neither Mark nor Evan works in data science, so measurement might have been the easy thing to skip. Instead, they shipped a product with built‑in measurement from…
Chris Blower

From Messages to Episodes: Building Better Recall for AI Support

Our customers do not think of support as isolated chats. They think in terms of things they are trying to get done: connecting a domain, changing the look of a site, launching a store, fixing checkout, recovering access, or understanding a bill. That creates a challenge for an AI support assistant. If a customer returns and says: Let’s…
João Amaral

Bringing Metadata to Life at Automattic with OpenMetadata

The metadata problem at scale Automattic’s data ecosystem is large and highly interconnected: thousands of Iceberg tables and views queried via Trino, thousands of Airflow tasks producing and updating them via Spark jobs, and a growing catalogue of Looker and Superset dashboards and charts on top. Most of the information about these assets exists somewhere, scattered…
Fırat

From Default to Delightful: AI-Assisted Data Visualization

I can never remember the exact syntax for visualization libraries. AI changes this. Now I describe what I want in natural language, iterate in conversation, and let the model handle the boilerplate. Five prompts transformed default charts into a visual story of WordPress’s 20-year evolution.
Paulina Hetman

AI-powered Typo Hunting: Trust Your Docs, Readers Will

Paulina explains how she proactively addresses the typos in Jetpack.com support pages. She developed an automated solution using the WordPress.com API and GPT-4o model.