The store · stack
The Content Engine
4 systemsHow a piece of content gets made, goes live, and gets found.
The end-to-end path content travels here: multi-agent enrichment writes and cross-links it, the seeders push it into the live database, the semantic index makes it findable, and one command registry routes people to it.
Enrichment Orchestrator
Five-agent pipeline that writes SEO metadata for every asset.
The most-used custom workflow on the site: five sub-agents (auditor, blog, content, linker, metadata) that audit, draft, and cross-link content, then write it to Supabase. Token usage and cost are tracked per run.
Content Seeders
The bridge that pushes committed content into the live database.
Blog, research and projects content is Supabase-driven. The seeders upsert committed seed sources into the main project so content reaches the live site, then rebuild the semantic search index. Auto-runs on merge.
Semantic Search Index
Voyage embeddings + hybrid grounding for the concierge.
The semantic layer behind the site’s Ask/concierge: a content-embedding pipeline (Voyage) that indexes blog, research and projects, rebuilt on every content merge, then queried as hybrid keyword-plus-vector grounding so answers cite real pages. A freshness check guards against staleness.
Command Registry
One declarative list of every destination and action on the site.
A single source of truth for the site’s stable destinations and actions, role-gated and grouped. The nav, footer sitemap, omnibar and concierge all read it — so they never re-derive their own lists.