Workshop Notes

Shelf is a Shopify app that gives merchants a daily briefing on what their competitors are doing — prices, inventory signals, stock levels. It crawls rival storefronts with Playwright, passes the signals through a four-layer AI pipeline, and surfaces the output inside the merchant's Shopify admin.

How we built a production Shopify competitor intelligence app end to end — the stack, the pipeline, the prompting mistakes, and what the discipline actually gave us.

A dense, stateful UI surface built with AI doing the assembly — what worked, what drifted, and where hands had to stay on the wheel.

We used Langflow to sketch agentic patterns before hardcoding them in Python. We wired it to a local Postgres with production-level data. Here's what we learned and where we're still stuck.

What 250K context actually feels like in production. How we structure long-running prompt jobs on Shelf, what the industry is beginning to understand about this shift, and why we haven't really cracked it yet.

The real eval stack behind migrating a production LLM prompt on Shelf — a 32-check scoring rubric, a one-way runner, 54 adversarial payloads, Pydantic strict validation, and a hard rule about who can approve a prompt edit.

killdate-kit, Orrery, vizstack and agentviz — everything we've released, with links and how each was built.

They're how-tos, so they file under method — built for Shelf, linked from here.