Blog

Thinking in Public

Architecture decisions, product thinking, and the mechanics of making AI search actually work for e-commerce brands.

Architecture2026-02-175 min

The Industry Is Building the Wrong Thing

Everyone is building AI dashboards. Nobody is building AI systems that safely execute. The future of catalog intelligence isn't smarter screens. It's separated architecture.

Read post

Architecture2026-02-164 min

Every Platform Speaks a Different Language

Shopify uses metafields. WooCommerce uses custom attributes. Feeds flatten everything into TSV columns. Without a canonical schema, your AI agent is just guessing.

Read post

Architecture2026-02-153 min

The Most Dangerous Shortcut in AI

You can point GPT-4 at your catalog and say 'fix it.' For ten products, it works. For five thousand, it breaks in ways you won't notice until the damage is done.

Read post

Engineering2026-02-143 min

Nothing Touches Production Without a Trail

In EKOM, there is no code path from a chat message to a production write. Every change is a versioned patch. Every patch has a reason. Every reason has a record.

Read post

Product2026-02-133 min

You Can't Measure What Doesn't Share

AI platforms don't provide analytics to brands. There is no Google Analytics for LLMs. Visibility measurement is synthetic and directional, and it's still a step change from zero.

Read post

Product2026-02-123 min

A Dashboard Never Fixed Anything

The e-commerce tooling market spent a decade building dashboards. They show you what's broken. Then they leave. EKOM doesn't monitor. It acts.

Read post

Engineering2026-02-247 min

We Tried to Build One Engine. We Needed Three.

We started with meta titles. Then descriptions. Then colors, materials, GTINs. That's when we realized: different fields need fundamentally different systems. Here's the framework that emerged.

Read post